Fix code review issues from PR #30#31
Open
jeremyeder wants to merge 2 commits intoambient-code:mainfrom
Open
Conversation
Install spec-kit commands, scripts, and templates from github/spec-kit. Add spec-kit-auto skill that autonomously chains /speckit.specify, /speckit.plan, /speckit.tasks, /speckit.analyze, and /speckit.implement with inline lint/security/finish phases. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix broken path reference in speckit.constitution.md (.specify/templates/commands/*.md → .claude/commands/speckit.*.md) - Regenerate .repomap.txt to reflect new files - Add .worktrees/ to .gitignore Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
WalkthroughThis pull request introduces a comprehensive specification-driven development framework called "speckit" comprising Claude command definitions, Bash utility scripts, Markdown templates, a skill orchestration definition, plugin configuration, and initialization options for automated feature specification, planning, task generation, implementation, and quality analysis workflows. Changes
Estimated code review effort🎯 4 (Complex) | ⏱️ ~75 minutes 🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 18
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.claude/commands/speckit.clarify.md:
- Line 25: Update the documentation line that invokes the script to remove the
unsupported aliases `-Json` and `-PathsOnly` and only reference the real CLI
flags `--json` and `--paths-only` (lowercase, dashed); specifically change the
example invocation of check-prerequisites.sh (the string containing
`.specify/scripts/bash/check-prerequisites.sh --json --paths-only`) so it no
longer lists `-Json -PathsOnly`, and ensure surrounding text/references mention
the exact supported flags only.
In @.claude/commands/speckit.implement.md:
- Around line 25-44: The markdown fences in the Extension Hooks examples are
missing blank lines around the triple-backticks and lack a fence language,
causing MD031/MD040 failures; update each fenced code block around the "##
Extension Hooks" examples (the optional pre-hook and mandatory hook blocks
shown) to add a blank line before and after each ``` fence and add a fence
language (use "text") so each block starts with ```text and ends with ``` with a
blank line following the closing fence.
- Line 171: Update the ordered list item at Line 171 in
.claude/commands/speckit.implement.md so it restarts numbering instead of using
"10."; replace the "10." prefix on the line that begins "10. **Check for
extension hooks**: After completion validation, check if
`.specify/extensions.yml` exists in the project root." with "1." (or the
appropriate restart marker) to comply with MD029 ordered-list style.
In @.claude/commands/speckit.plan.md:
- Around line 61-71: The document references Phase 0 and Phase 1 but instructs
to "stop after Phase 2 planning," creating an ambiguous termination point;
update the IMPL_PLAN steps so the phase boundary is consistent by either (A)
changing the stop instruction to "stop after Phase 1 planning" to match the
listed phases, or (B) adding a clear Phase 2 definition and steps into the
numbered workflow (including how it affects Technical Context, Constitution
Check, gates, and artifacts) so that IMPL_PLAN, Phase 0, Phase 1, and Phase 2
are all explicitly defined and consistent.
In @.claude/commands/speckit.specify.md:
- Around line 81-82: The PowerShell examples call the Bash script
`.specify/scripts/bash/create-new-feature.sh` with incorrect PascalCase short
flags (`-Json`, `-ShortName`, `-Timestamp`) which will be treated as positional
args; update the examples to use the script's lowercase kebab-case flags
(`--json`, `--short-name`, `--timestamp`) so the options are parsed correctly,
or alternatively add a PowerShell wrapper that maps
`-Json`/`-ShortName`/`-Timestamp` to `--json`/`--short-name`/`--timestamp`
before invoking `create-new-feature.sh`.
- Around line 79-80: The Bash examples for
`.specify/scripts/bash/create-new-feature.sh` currently pass the feature
description twice (via "$ARGUMENTS" and the literal "Add user authentication");
update both examples (the plain and the timestamp variant) to provide the
description only once by removing the duplicated literal description so the
script receives either "$ARGUMENTS" or the quoted description but not both;
ensure the examples still include the flags `--json`/`--timestamp` and
`--short-name "user-auth"` and verify that `$ARGUMENTS` remains in the example
if you want to demonstrate passing arguments via the variable.
In @.claude/skills/spec-kit-auto/SKILL.md:
- Line 79: Change the lowercase platform name "GitHub" in prose to the proper
capitalized form while leaving filesystem path fragments like
".github/workflows/*.yml" unchanged; specifically update the descriptive text
around the table row containing `.github/workflows/*.yml | actionlint |
actionlint` and the other occurrence near the later mention (the text at the
location referenced as 115-115) to use "GitHub" instead of "Github" or "github".
In @.repomap.txt:
- Around line 15-63: The repomap generator is mis-parsing Bash function names in
.specify/scripts/bash/update-agent-context.sh (e.g., producing g_info(),
g_success(), error(), warning(), nup(), date_environment(), act_plan_field(),
e_plan_data(), at_technology_stack(), project_structure(),
commands_for_language(), language_conventions(), te_new_agent_file(),
te_existing_agent_file(), te_agent_file(), te_specific_agent(), if_new(),
ll_existing_agents(), mmary()); update the parser so it correctly recognizes
Bash function declaration patterns (handles "name()", "name ()", "function
name()", and multiline/header comments) and map the parsed identifiers to the
real function names (log_info, log_success, log_error, log_warning, cleanup,
validate_environment, extract_plan_field, parse_plan_data,
format_technology_stack, get_project_structure, get_commands_for_language,
get_language_conventions, create_new_agent_file, update_existing_agent_file,
update_agent_file, update_specific_agent, _update_if_new,
update_all_existing_agents, print_summary) then regenerate .repomap.txt (or
replace the parsing step with a robust shell AST/tokenizer) so entries are not
corrupted.
In @.specify/init-options.json:
- Line 5: The branch_numbering setting in .specify/init-options.json is unused
by the create-new-feature.sh flow; update the create-new-feature.sh script to
read the "branch_numbering" value (e.g., export or set a BRANCH_NUMBERING
variable) at startup and use it to control branch naming unless an explicit
--timestamp flag is provided, so the script's branch name generation logic (the
code handling --timestamp and sequential/timestamp decision) honors
branch_numbering by default; ensure precedence: CLI --timestamp overrides
config, otherwise use branch_numbering ("sequential" vs "timestamp") to pick the
naming strategy.
In @.specify/scripts/bash/common.sh:
- Line 57: The current line "local repo_root=$(get_repo_root)" masks any
non-zero return from get_repo_root (SC2155); fix by declaring the variable and
assigning in two steps: first declare local repo_root, then assign repo_root by
calling get_repo_root (use command substitution with quotes, e.g.,
repo_root="$(get_repo_root)") so failures are not masked; update the code around
the local repo_root usage to use the newly assigned variable.
- Around line 44-45: The combined declaration and command-substitution masks
subshell failures; split declaration and assignment so failures from the
subshell propagate: first declare local script_dir, then perform the command
substitution/ subshell to compute the path and assign to script_dir (e.g., run
the cd/pwd subshell in a separate statement and set script_dir from its output),
ensuring any non-zero exit from the subshell is not masked; update references to
the variable name script_dir accordingly.
In @.specify/scripts/bash/create-new-feature.sh:
- Around line 31-43: The --number parsing branch currently sets BRANCH_NUMBER
without validation which later causes a cryptic failure at the arithmetic
expansion $((10#$BRANCH_NUMBER)); update the --number case (the --number) to
validate next_arg before assigning it to BRANCH_NUMBER: ensure it matches a
non-negative integer regex (e.g., ^[0-9]+$), reject empty/negative/alpha values
with a clear error message and exit non-zero, and only then assign
BRANCH_NUMBER; additionally ensure any later use of $((10#$BRANCH_NUMBER)) can
rely on this validation (no further change required if validation passes).
In @.specify/scripts/bash/setup-plan.sh:
- Around line 41-50: The current setup script unconditionally copies the
resolved TEMPLATE into IMPL_PLAN which will overwrite any existing user plan;
update the logic in the block that uses resolve_template and TEMPLATE to first
check if IMPL_PLAN already exists and is non-empty (e.g., test -e or -s on
IMPL_PLAN) and only perform cp "$TEMPLATE" "$IMPL_PLAN" when the plan file does
not exist or is empty; if IMPL_PLAN exists, skip copying and log a message
instead so user content is preserved.
- Around line 7-24: The ARGS array is populated in the argument-parsing loop but
never used; remove the unused ARGS variable and the ARGS+=("$arg") branch from
the case in setup-plan.sh (or alternatively, if non-option arguments are
intended to be handled, implement consuming/using ARGS after parsing). Update
the loop to only handle --json and --help (and default to reporting/ignoring
unexpected args) and remove the ARGS declaration to eliminate the
unused-variable warning; reference the ARGS variable and the argument-parsing
case block around the for arg in "$@" loop and JSON_MODE handling when making
the change.
In @.specify/scripts/bash/update-agent-context.sh:
- Around line 196-199: The create-path branch in
parse_plan_data/extract_plan_field sets NEW_DB but never adds it to the new
context's tech_stack or recent_change, so include NEW_DB (the Storage value
returned by extract_plan_field) when assembling the tech_stack array and append
it to recent_change in the "create" flow just as the update flow does; mirror
the same logic you use for NEW_LANG/NEW_FRAMEWORK (the variables set by
extract_plan_field) when building the initial context and apply the same fix to
the analogous create branch around the other occurrence mentioned (the block
similar to lines 323-343).
- Around line 465-483: The Recent Changes block is not idempotent because the
script always echoes new_change_entry, causing duplicates; fix by detecting
whether new_change_entry already exists in that section before adding it: when
you enter the "## Recent Changes" branch (use the in_changes_section variable
and the new_change_entry variable), scan the following lines (until the next "##
" heading) for a line equal to new_change_entry and set a flag like
new_change_present; only echo new_change_entry into the temp_file if
new_change_present is false, and ensure existing_changes_count logic still
copies at most two unique bullets (skip lines equal to new_change_entry while
counting) so reruns won't prepend a duplicate.
- Around line 318-320: The sed replacement values are not properly escaped for
replacement text (specials like &, | and \), so add a small helper (e.g.
escape_sed_replacement) that escapes backslashes, ampersands and your chosen sed
delimiter (|) and then use it to produce escaped versions of NEW_LANG,
NEW_FRAMEWORK, CURRENT_BRANCH and also the other replacement values used in the
substitutions array (project_name, current_date, project_structure, commands,
language_conventions); replace the current printf/sed regex-escape usage with
calls to this helper and use the escaped_* variables when building the
substitutions array and invoking sed.
In @.specify/templates/plan-template.md:
- Line 6: Update the misleading self-reference in the note: change the execution
workflow link text in .specify/templates/plan-template.md so it no longer points
to the same template but instead references the command workflow document (e.g.,
.claude/commands/speckit.plan.md) and the /speckit.plan command; edit the
sentence beginning "**Note**: This template is filled in by the `/speckit.plan`
command. See `.specify/templates/plan-template.md` for the execution workflow."
to point to the proper workflow doc (.claude/commands/speckit.plan.md) and
ensure the phrasing clearly ties the template to the `/speckit.plan` command.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: 6ec57547-23d6-47ca-acbe-e9a02e15f66a
📒 Files selected for processing (26)
.claude-plugin/plugin.json.claude/commands/speckit.analyze.md.claude/commands/speckit.checklist.md.claude/commands/speckit.clarify.md.claude/commands/speckit.constitution.md.claude/commands/speckit.implement.md.claude/commands/speckit.plan.md.claude/commands/speckit.specify.md.claude/commands/speckit.tasks.md.claude/commands/speckit.taskstoissues.md.claude/skills/spec-kit-auto/SKILL.md.gitignore.repomap.txt.specify/init-options.json.specify/memory/constitution.md.specify/scripts/bash/check-prerequisites.sh.specify/scripts/bash/common.sh.specify/scripts/bash/create-new-feature.sh.specify/scripts/bash/setup-plan.sh.specify/scripts/bash/update-agent-context.sh.specify/templates/agent-file-template.md.specify/templates/checklist-template.md.specify/templates/constitution-template.md.specify/templates/plan-template.md.specify/templates/spec-template.md.specify/templates/tasks-template.md
|
|
||
| Execution steps: | ||
|
|
||
| 1. Run `.specify/scripts/bash/check-prerequisites.sh --json --paths-only` from repo root **once** (combined `--json --paths-only` mode / `-Json -PathsOnly`). Parse minimal JSON payload fields: |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Confirm supported options in the prerequisites script.
rg -n -C2 -- '--json|--paths-only|-Json|-PathsOnly' .specify/scripts/bash/check-prerequisites.shRepository: ambient-code/reference
Length of output: 1341
Remove unsupported -Json -PathsOnly aliases.
Line 25 references flag aliases that are not supported by check-prerequisites.sh. The script documentation and argument parsing only support --json and --paths-only (lowercase with dashes). Including the unsupported aliases creates confusion and contradicts the actual CLI interface.
Proposed fix
-1. Run `.specify/scripts/bash/check-prerequisites.sh --json --paths-only` from repo root **once** (combined `--json --paths-only` mode / `-Json -PathsOnly`). Parse minimal JSON payload fields:
+1. Run `.specify/scripts/bash/check-prerequisites.sh --json --paths-only` from repo root **once** (combined `--json --paths-only` mode). Parse minimal JSON payload fields:📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| 1. Run `.specify/scripts/bash/check-prerequisites.sh --json --paths-only` from repo root **once** (combined `--json --paths-only` mode / `-Json -PathsOnly`). Parse minimal JSON payload fields: | |
| 1. Run `.specify/scripts/bash/check-prerequisites.sh --json --paths-only` from repo root **once** (combined `--json --paths-only` mode). Parse minimal JSON payload fields: |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.claude/commands/speckit.clarify.md at line 25, Update the documentation
line that invokes the script to remove the unsupported aliases `-Json` and
`-PathsOnly` and only reference the real CLI flags `--json` and `--paths-only`
(lowercase, dashed); specifically change the example invocation of
check-prerequisites.sh (the string containing
`.specify/scripts/bash/check-prerequisites.sh --json --paths-only`) so it no
longer lists `-Json -PathsOnly`, and ensure surrounding text/references mention
the exact supported flags only.
Comment on lines
+25
to
+44
| ``` | ||
| ## Extension Hooks | ||
|
|
||
| **Optional Pre-Hook**: {extension} | ||
| Command: `/{command}` | ||
| Description: {description} | ||
|
|
||
| Prompt: {prompt} | ||
| To execute: `/{command}` | ||
| ``` | ||
| - **Mandatory hook** (`optional: false`): | ||
| ``` | ||
| ## Extension Hooks | ||
|
|
||
| **Automatic Pre-Hook**: {extension} | ||
| Executing: `/{command}` | ||
| EXECUTE_COMMAND: {command} | ||
|
|
||
| Wait for the result of the hook command before proceeding to the Outline. | ||
| ``` |
There was a problem hiding this comment.
Fix fenced code block formatting to unblock markdownlint.
Lines in these ranges are failing MD031/MD040 (missing blank lines around fences and missing fence language), which is currently breaking the documentation validation pipeline.
Proposed lint-compliant fence format
- ```
+
+ ```text
## Extension Hooks
@@
- ```
+ ```
+
@@
- ```
+
+ ```text
## Extension Hooks
@@
- ```
+ ```
+
@@
- ```
+
+ ```text
## Extension Hooks
@@
- ```
+ ```
+
@@
- ```
+
+ ```text
## Extension Hooks
@@
- ```
+ ```
+ Also applies to: 180-197
🧰 Tools
🪛 GitHub Actions: Documentation Validation
[error] 25-25: markdownlint-cli2 (markdownlint v0.33.0): MD031/blanks-around-fences — Fenced code blocks should be surrounded by blank lines [Context: "```"]
🪛 GitHub Check: lint-markdown
[failure] 44-44: Fenced code blocks should be surrounded by blank lines
.claude/commands/speckit.implement.md:44 MD031/blanks-around-fences Fenced code blocks should be surrounded by blank lines [Context: "```"] https://github.com/DavidAnson/markdownlint/blob/v0.33.0/doc/md031.md
[failure] 36-36: Fenced code blocks should have a language specified
.claude/commands/speckit.implement.md:36 MD040/fenced-code-language Fenced code blocks should have a language specified [Context: " ```"] https://github.com/DavidAnson/markdownlint/blob/v0.33.0/doc/md040.md
[failure] 36-36: Fenced code blocks should be surrounded by blank lines
.claude/commands/speckit.implement.md:36 MD031/blanks-around-fences Fenced code blocks should be surrounded by blank lines [Context: "```"] https://github.com/DavidAnson/markdownlint/blob/v0.33.0/doc/md031.md
[failure] 34-34: Fenced code blocks should be surrounded by blank lines
.claude/commands/speckit.implement.md:34 MD031/blanks-around-fences Fenced code blocks should be surrounded by blank lines [Context: "```"] https://github.com/DavidAnson/markdownlint/blob/v0.33.0/doc/md031.md
[failure] 25-25: Fenced code blocks should have a language specified
.claude/commands/speckit.implement.md:25 MD040/fenced-code-language Fenced code blocks should have a language specified [Context: " ```"] https://github.com/DavidAnson/markdownlint/blob/v0.33.0/doc/md040.md
[failure] 25-25: Fenced code blocks should be surrounded by blank lines
.claude/commands/speckit.implement.md:25 MD031/blanks-around-fences Fenced code blocks should be surrounded by blank lines [Context: "```"] https://github.com/DavidAnson/markdownlint/blob/v0.33.0/doc/md031.md
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.claude/commands/speckit.implement.md around lines 25 - 44, The markdown
fences in the Extension Hooks examples are missing blank lines around the
triple-backticks and lack a fence language, causing MD031/MD040 failures; update
each fenced code block around the "## Extension Hooks" examples (the optional
pre-hook and mandatory hook blocks shown) to add a blank line before and after
each ``` fence and add a fence language (use "text") so each block starts with
```text and ends with ``` with a blank line following the closing fence.
|
|
||
| Note: This command assumes a complete task breakdown exists in tasks.md. If tasks are incomplete or missing, suggest running `/speckit.tasks` first to regenerate the task list. | ||
|
|
||
| 10. **Check for extension hooks**: After completion validation, check if `.specify/extensions.yml` exists in the project root. |
There was a problem hiding this comment.
Restart ordered-list numbering at Line 171.
Line 171 uses 10. as a new list start, which violates the configured ordered-list style (MD029) and fails lint.
Proposed fix
-10. **Check for extension hooks**: After completion validation, check if `.specify/extensions.yml` exists in the project root.
+1. **Check for extension hooks**: After completion validation, check if `.specify/extensions.yml` exists in the project root.📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| 10. **Check for extension hooks**: After completion validation, check if `.specify/extensions.yml` exists in the project root. | |
| 1. **Check for extension hooks**: After completion validation, check if `.specify/extensions.yml` exists in the project root. |
🧰 Tools
🪛 GitHub Check: lint-markdown
[failure] 171-171: Ordered list item prefix
.claude/commands/speckit.implement.md:171:1 MD029/ol-prefix Ordered list item prefix [Expected: 1; Actual: 10; Style: 1/1/1] https://github.com/DavidAnson/markdownlint/blob/v0.33.0/doc/md029.md
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.claude/commands/speckit.implement.md at line 171, Update the ordered list
item at Line 171 in .claude/commands/speckit.implement.md so it restarts
numbering instead of using "10."; replace the "10." prefix on the line that
begins "10. **Check for extension hooks**: After completion validation, check if
`.specify/extensions.yml` exists in the project root." with "1." (or the
appropriate restart marker) to comply with MD029 ordered-list style.
Comment on lines
+61
to
+71
| 3. **Execute plan workflow**: Follow the structure in IMPL_PLAN template to: | ||
| - Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION") | ||
| - Fill Constitution Check section from constitution | ||
| - Evaluate gates (ERROR if violations unjustified) | ||
| - Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION) | ||
| - Phase 1: Generate data-model.md, contracts/, quickstart.md | ||
| - Phase 1: Update agent context by running the agent script | ||
| - Re-evaluate Constitution Check post-design | ||
|
|
||
| 4. **Stop and report**: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts. | ||
|
|
There was a problem hiding this comment.
Clarify phase boundary to prevent ambiguous termination.
Line 70 says to stop after “Phase 2 planning,” but the outlined workflow defines Phase 0 and Phase 1 only. This creates conflicting execution guidance.
Proposed doc fix
-4. **Stop and report**: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts.
+4. **Stop and report**: Command ends after Phase 1 design planning artifacts are produced. Report branch, IMPL_PLAN path, and generated artifacts.📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| 3. **Execute plan workflow**: Follow the structure in IMPL_PLAN template to: | |
| - Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION") | |
| - Fill Constitution Check section from constitution | |
| - Evaluate gates (ERROR if violations unjustified) | |
| - Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION) | |
| - Phase 1: Generate data-model.md, contracts/, quickstart.md | |
| - Phase 1: Update agent context by running the agent script | |
| - Re-evaluate Constitution Check post-design | |
| 4. **Stop and report**: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts. | |
| 3. **Execute plan workflow**: Follow the structure in IMPL_PLAN template to: | |
| - Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION") | |
| - Fill Constitution Check section from constitution | |
| - Evaluate gates (ERROR if violations unjustified) | |
| - Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION) | |
| - Phase 1: Generate data-model.md, contracts/, quickstart.md | |
| - Phase 1: Update agent context by running the agent script | |
| - Re-evaluate Constitution Check post-design | |
| 4. **Stop and report**: Command ends after Phase 1 design planning artifacts are produced. Report branch, IMPL_PLAN path, and generated artifacts. |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.claude/commands/speckit.plan.md around lines 61 - 71, The document
references Phase 0 and Phase 1 but instructs to "stop after Phase 2 planning,"
creating an ambiguous termination point; update the IMPL_PLAN steps so the phase
boundary is consistent by either (A) changing the stop instruction to "stop
after Phase 1 planning" to match the listed phases, or (B) adding a clear Phase
2 definition and steps into the numbered workflow (including how it affects
Technical Context, Constitution Check, gates, and artifacts) so that IMPL_PLAN,
Phase 0, Phase 1, and Phase 2 are all explicitly defined and consistent.
Comment on lines
+79
to
+80
| - Bash example: `.specify/scripts/bash/create-new-feature.sh "$ARGUMENTS" --json --short-name "user-auth" "Add user authentication"` | ||
| - Bash (timestamp): `.specify/scripts/bash/create-new-feature.sh "$ARGUMENTS" --json --timestamp --short-name "user-auth" "Add user authentication"` |
There was a problem hiding this comment.
Pass the feature description only once in the Bash examples.
create-new-feature.sh concatenates every non-option argument into the description, so keeping both $ARGUMENTS and "Add user authentication" here duplicates the feature text and can change the generated branch/spec names.
Suggested fix
- - Bash example: `.specify/scripts/bash/create-new-feature.sh "$ARGUMENTS" --json --short-name "user-auth" "Add user authentication"`
- - Bash (timestamp): `.specify/scripts/bash/create-new-feature.sh "$ARGUMENTS" --json --timestamp --short-name "user-auth" "Add user authentication"`
+ - Bash example: `.specify/scripts/bash/create-new-feature.sh --json --short-name "user-auth" "$ARGUMENTS"`
+ - Bash (timestamp): `.specify/scripts/bash/create-new-feature.sh --json --timestamp --short-name "user-auth" "$ARGUMENTS"`📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| - Bash example: `.specify/scripts/bash/create-new-feature.sh "$ARGUMENTS" --json --short-name "user-auth" "Add user authentication"` | |
| - Bash (timestamp): `.specify/scripts/bash/create-new-feature.sh "$ARGUMENTS" --json --timestamp --short-name "user-auth" "Add user authentication"` | |
| - Bash example: `.specify/scripts/bash/create-new-feature.sh --json --short-name "user-auth" "$ARGUMENTS"` | |
| - Bash (timestamp): `.specify/scripts/bash/create-new-feature.sh --json --timestamp --short-name "user-auth" "$ARGUMENTS"` |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.claude/commands/speckit.specify.md around lines 79 - 80, The Bash examples
for `.specify/scripts/bash/create-new-feature.sh` currently pass the feature
description twice (via "$ARGUMENTS" and the literal "Add user authentication");
update both examples (the plain and the timestamp variant) to provide the
description only once by removing the duplicated literal description so the
script receives either "$ARGUMENTS" or the quoted description but not both;
ensure the examples still include the flags `--json`/`--timestamp` and
`--short-name "user-auth"` and verify that `$ARGUMENTS` remains in the example
if you want to demonstrate passing arguments via the variable.
Comment on lines
+41
to
+50
| # Copy plan template if it exists | ||
| TEMPLATE=$(resolve_template "plan-template" "$REPO_ROOT") || true | ||
| if [[ -n "$TEMPLATE" ]] && [[ -f "$TEMPLATE" ]]; then | ||
| cp "$TEMPLATE" "$IMPL_PLAN" | ||
| echo "Copied plan template to $IMPL_PLAN" | ||
| else | ||
| echo "Warning: Plan template not found" | ||
| # Create a basic plan file if template doesn't exist | ||
| touch "$IMPL_PLAN" | ||
| fi |
There was a problem hiding this comment.
Template copy overwrites existing plan unconditionally.
If $IMPL_PLAN already exists with user content, this will overwrite it. Consider checking if the file exists first and only copying the template when creating a new plan.
🛡️ Proposed fix
# Copy plan template if it exists
TEMPLATE=$(resolve_template "plan-template" "$REPO_ROOT") || true
-if [[ -n "$TEMPLATE" ]] && [[ -f "$TEMPLATE" ]]; then
- cp "$TEMPLATE" "$IMPL_PLAN"
- echo "Copied plan template to $IMPL_PLAN"
-else
- echo "Warning: Plan template not found"
- # Create a basic plan file if template doesn't exist
- touch "$IMPL_PLAN"
+if [[ ! -f "$IMPL_PLAN" ]]; then
+ if [[ -n "$TEMPLATE" ]] && [[ -f "$TEMPLATE" ]]; then
+ cp "$TEMPLATE" "$IMPL_PLAN"
+ echo "Copied plan template to $IMPL_PLAN"
+ else
+ echo "Warning: Plan template not found"
+ # Create a basic plan file if template doesn't exist
+ touch "$IMPL_PLAN"
+ fi
+else
+ echo "Plan already exists: $IMPL_PLAN"
fi🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.specify/scripts/bash/setup-plan.sh around lines 41 - 50, The current setup
script unconditionally copies the resolved TEMPLATE into IMPL_PLAN which will
overwrite any existing user plan; update the logic in the block that uses
resolve_template and TEMPLATE to first check if IMPL_PLAN already exists and is
non-empty (e.g., test -e or -s on IMPL_PLAN) and only perform cp "$TEMPLATE"
"$IMPL_PLAN" when the plan file does not exist or is empty; if IMPL_PLAN exists,
skip copying and log a message instead so user content is preserved.
Comment on lines
+196
to
+199
| NEW_LANG=$(extract_plan_field "Language/Version" "$plan_file") | ||
| NEW_FRAMEWORK=$(extract_plan_field "Primary Dependencies" "$plan_file") | ||
| NEW_DB=$(extract_plan_field "Storage" "$plan_file") | ||
| NEW_PROJECT_TYPE=$(extract_plan_field "Project Type" "$plan_file") |
There was a problem hiding this comment.
A brand-new context file drops the extracted storage technology.
parse_plan_data captures Storage into NEW_DB, and the update path later adds it under Active Technologies, but the create path never includes NEW_DB in either tech_stack or recent_change. Repositories getting their first context file will therefore lose the database/storage choice entirely.
Also applies to: 323-343
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.specify/scripts/bash/update-agent-context.sh around lines 196 - 199, The
create-path branch in parse_plan_data/extract_plan_field sets NEW_DB but never
adds it to the new context's tech_stack or recent_change, so include NEW_DB (the
Storage value returned by extract_plan_field) when assembling the tech_stack
array and append it to recent_change in the "create" flow just as the update
flow does; mirror the same logic you use for NEW_LANG/NEW_FRAMEWORK (the
variables set by extract_plan_field) when building the initial context and apply
the same fix to the analogous create branch around the other occurrence
mentioned (the block similar to lines 323-343).
Comment on lines
+318
to
+320
| local escaped_lang=$(printf '%s\n' "$NEW_LANG" | sed 's/[\[\.*^$()+{}|]/\\&/g') | ||
| local escaped_framework=$(printf '%s\n' "$NEW_FRAMEWORK" | sed 's/[\[\.*^$()+{}|]/\\&/g') | ||
| local escaped_branch=$(printf '%s\n' "$CURRENT_BRANCH" | sed 's/[\[\.*^$()+{}|]/\\&/g') |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
set -euo pipefail
tmp=$(mktemp)
trap 'rm -f "$tmp" "$tmp".bak' EXIT
printf '[EXTRACTED FROM ALL PLAN.MD FILES]\n' > "$tmp"
NEW_LANG='Node.js'
NEW_FRAMEWORK='R&D + C++'
CURRENT_BRANCH='20260401-demo'
escaped_lang=$(printf '%s\n' "$NEW_LANG" | sed 's/[\[\.*^$()+{}|]/\\&/g')
escaped_framework=$(printf '%s\n' "$NEW_FRAMEWORK" | sed 's/[\[\.*^$()+{}|]/\\&/g')
escaped_branch=$(printf '%s\n' "$CURRENT_BRANCH" | sed 's/[\[\.*^$()+{}|]/\\&/g')
tech_stack="- $escaped_lang + $escaped_framework ($escaped_branch)"
sed -i.bak -e "s|\[EXTRACTED FROM ALL PLAN.MD FILES\]|$tech_stack|" "$tmp" || true
cat "$tmp"Repository: ambient-code/reference
Length of output: 136
🏁 Script executed:
# First, let's look at the file and the specific line ranges mentioned
cd /root/codebase || cd . 2>/dev/null
find . -name "update-agent-context.sh" -type f 2>/dev/null | head -20Repository: ambient-code/reference
Length of output: 195
🏁 Script executed:
find . -path "*/.specify/scripts/bash/update-agent-context.sh" -type f 2>/dev/nullRepository: ambient-code/reference
Length of output: 113
🏁 Script executed:
# Search more broadly
fd -i "update-agent-context" . 2>/dev/null | head -20Repository: ambient-code/reference
Length of output: 48
🏁 Script executed:
# List the directory structure if it exists
ls -la .specify/scripts/bash/ 2>/dev/null || echo "Directory not found, searching..."
find . -type d -name ".specify" 2>/dev/nullRepository: ambient-code/reference
Length of output: 533
🏁 Script executed:
# Search in git to find the file
git ls-files | grep -i "update-agent-context"Repository: ambient-code/reference
Length of output: 111
🏁 Script executed:
# Examine the specific lines mentioned in the review
sed -n '315,325p' ./.specify/scripts/bash/update-agent-context.shRepository: ambient-code/reference
Length of output: 728
🏁 Script executed:
# Also check lines 345-357
sed -n '340,360p' ./.specify/scripts/bash/update-agent-context.shRepository: ambient-code/reference
Length of output: 922
🏁 Script executed:
# Search for all uses of escaped_lang, escaped_framework, escaped_branch
grep -n "escaped_" ./.specify/scripts/bash/update-agent-context.shRepository: ambient-code/reference
Length of output: 1199
🏁 Script executed:
# Get context around all sed substitutions to understand the full scope
grep -n "sed.*escaped" ./.specify/scripts/bash/update-agent-context.shRepository: ambient-code/reference
Length of output: 48
🏁 Script executed:
# Check what other variables are used in the substitutions array
sed -n '344,360p' ./.specify/scripts/bash/update-agent-context.shRepository: ambient-code/reference
Length of output: 789
🏁 Script executed:
# Look for all variable assignments that might be used in sed replacements
grep -n "project_name\|project_structure\|commands\|language_conventions" ./.specify/scripts/bash/update-agent-context.sh | head -20Repository: ambient-code/reference
Length of output: 1038
🏁 Script executed:
# Search for where these other variables are defined to see if they're escaped
grep -n "^[[:space:]]*local.*=" ./.specify/scripts/bash/update-agent-context.sh | head -30Repository: ambient-code/reference
Length of output: 1257
🏁 Script executed:
# Let me trace where project_name, project_structure, commands, language_conventions come from
# to understand what they contain
# Check the get_project_structure function
sed -n '249,258p' ./.specify/scripts/bash/update-agent-context.shRepository: ambient-code/reference
Length of output: 263
🏁 Script executed:
# Check the get_commands_for_language function
sed -n '259,277p' ./.specify/scripts/bash/update-agent-context.shRepository: ambient-code/reference
Length of output: 490
🏁 Script executed:
# Check the get_language_conventions function
sed -n '278,282p' ./.specify/scripts/bash/update-agent-context.shRepository: ambient-code/reference
Length of output: 163
🏁 Script executed:
# Let's create a comprehensive test to show ALL the escaping issues
cat > /tmp/test_escaping.sh << 'EOF'
#!/bin/bash
set -euo pipefail
tmp=$(mktemp)
trap 'rm -f "$tmp" "$tmp".bak' EXIT
printf '[PROJECT NAME] [COMMANDS] [LANG] [STRUCTURE]\n' > "$tmp"
# Simulate variables with problematic characters
project_name='My & Project'
commands='npm run build && npm test'
escaped_lang=$(printf '%s\n' 'Node.js' | sed 's/[\[\.*^$()+{}|]/\\&/g')
project_structure='src/ | tests/'
# Current approach - only escaped_lang is "escaped" for regex but NOT for replacement
tech_stack="- $escaped_lang"
echo "BEFORE:"
cat "$tmp"
echo -e "\nTrying substitutions with current approach:"
# This will fail/mangle because & isn't escaped for replacement text
sed -i.bak -e "s|\[PROJECT NAME\]|$project_name|" "$tmp" || true
sed -i.bak -e "s|\[COMMANDS\]|$commands|" "$tmp" || true
sed -i.bak -e "s|\[LANG\]|$tech_stack|" "$tmp" || true
sed -i.bak -e "s|\[STRUCTURE\]|$project_structure|" "$tmp" || true
echo "AFTER (broken):"
cat "$tmp"
EOF
bash /tmp/test_escaping.shRepository: ambient-code/reference
Length of output: 342
🏁 Script executed:
# Better test showing the specific & problem and delimiter problem
cat > /tmp/test_escaping2.sh << 'EOF'
#!/bin/bash
set -euo pipefail
tmp=$(mktemp)
trap 'rm -f "$tmp" "$tmp".bak' EXIT
printf '[PLACEHOLDER]\n' > "$tmp"
echo "=== Test 1: & character in replacement text ==="
value_with_ampersand='Research & Development'
sed -i.bak -e "s|\[PLACEHOLDER\]|$value_with_ampersand|" "$tmp" 2>&1 || echo "Failed"
cat "$tmp"
printf '[PLACEHOLDER]\n' > "$tmp"
echo -e "\n=== Test 2: Pipe character in replacement text ==="
value_with_pipe='option1 | option2'
sed -i.bak -e "s|\[PLACEHOLDER\]|$value_with_pipe|" "$tmp" 2>&1 || echo "Failed"
cat "$tmp"
printf '[PLACEHOLDER]\n' > "$tmp"
echo -e "\n=== Test 3: Backslash in replacement text ==="
value_with_backslash='path\\to\\file'
sed -i.bak -e "s|\[PLACEHOLDER\]|$value_with_backslash|" "$tmp" 2>&1 || echo "Failed"
cat "$tmp"
printf '[PLACEHOLDER]\n' > "$tmp"
echo -e "\n=== Test 4: Proper escaping for replacement text ==="
escape_sed_replacement() {
printf '%s' "$1" | sed 's/[&|\\]/\\&/g'
}
proper_escaped=$(escape_sed_replacement "R&D | Testing\\Path")
sed -i.bak -e "s|\[PLACEHOLDER\]|$proper_escaped|" "$tmp" 2>&1 || echo "Failed"
cat "$tmp"
EOF
bash /tmp/test_escaping2.shRepository: ambient-code/reference
Length of output: 408
🏁 Script executed:
# Verify the exact line range 345-357 that the review mentions
sed -n '345,357p' ./.specify/scripts/bash/update-agent-context.shRepository: ambient-code/reference
Length of output: 708
🏁 Script executed:
# Check if there are any other variables used in sed replacements that aren't escaped
grep -n "local substitutions" -A 15 ./.specify/scripts/bash/update-agent-context.sh | head -25Repository: ambient-code/reference
Length of output: 852
Escape all sed replacement text values to handle &, |, and \ properly.
The current approach only regex-escapes three variables (lines 318-320) for sed pattern matching, but these same values are used as sed replacement text where different characters need escaping. Additionally, four other unescaped variables (project_name, current_date, project_structure, commands, language_conventions) are directly interpolated into the replacements array (lines 345-352) without any escaping.
In sed replacement text:
&expands to the full matched pattern (breaks output)|is the chosen delimiter and causes syntax errors\has special meaning and needs escaping
Apply replacement text escaping to all seven variables used in the substitutions array:
Suggested direction
+escape_sed_replacement() {
+ printf '%s' "$1" | sed 's/[&|\\]/\\&/g'
+}Then escape each variable before use:
local escaped_lang=$(escape_sed_replacement "$NEW_LANG")
local escaped_framework=$(escape_sed_replacement "$NEW_FRAMEWORK")
local escaped_branch=$(escape_sed_replacement "$CURRENT_BRANCH")
local project_name=$(escape_sed_replacement "$(basename "$REPO_ROOT")")
local current_date=$(escape_sed_replacement "$(date +%Y-%m-%d)")
local project_structure=$(escape_sed_replacement "$(get_project_structure "$NEW_PROJECT_TYPE")")
local commands=$(escape_sed_replacement "$(get_commands_for_language "$NEW_LANG")")
local language_conventions=$(escape_sed_replacement "$(get_language_conventions "$NEW_LANG")")
🧰 Tools
🪛 Shellcheck (0.11.0)
[warning] 318-318: Declare and assign separately to avoid masking return values.
(SC2155)
[info] 318-318: Expressions don't expand in single quotes, use double quotes for that.
(SC2016)
[warning] 319-319: Declare and assign separately to avoid masking return values.
(SC2155)
[info] 319-319: Expressions don't expand in single quotes, use double quotes for that.
(SC2016)
[warning] 320-320: Declare and assign separately to avoid masking return values.
(SC2155)
[info] 320-320: Expressions don't expand in single quotes, use double quotes for that.
(SC2016)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.specify/scripts/bash/update-agent-context.sh around lines 318 - 320, The
sed replacement values are not properly escaped for replacement text (specials
like &, | and \), so add a small helper (e.g. escape_sed_replacement) that
escapes backslashes, ampersands and your chosen sed delimiter (|) and then use
it to produce escaped versions of NEW_LANG, NEW_FRAMEWORK, CURRENT_BRANCH and
also the other replacement values used in the substitutions array (project_name,
current_date, project_structure, commands, language_conventions); replace the
current printf/sed regex-escape usage with calls to this helper and use the
escaped_* variables when building the substitutions array and invoking sed.
Comment on lines
+465
to
+483
| if [[ "$line" == "## Recent Changes" ]]; then | ||
| echo "$line" >> "$temp_file" | ||
| # Add new change entry right after the heading | ||
| if [[ -n "$new_change_entry" ]]; then | ||
| echo "$new_change_entry" >> "$temp_file" | ||
| fi | ||
| in_changes_section=true | ||
| changes_entries_added=true | ||
| continue | ||
| elif [[ $in_changes_section == true ]] && [[ "$line" =~ ^##[[:space:]] ]]; then | ||
| echo "$line" >> "$temp_file" | ||
| in_changes_section=false | ||
| continue | ||
| elif [[ $in_changes_section == true ]] && [[ "$line" == "- "* ]]; then | ||
| # Keep only first 2 existing changes | ||
| if [[ $existing_changes_count -lt 2 ]]; then | ||
| echo "$line" >> "$temp_file" | ||
| ((existing_changes_count++)) | ||
| fi |
There was a problem hiding this comment.
The Recent Changes rewrite isn't idempotent.
Every run prepends new_change_entry and then copies the first two existing bullets. If the file already contains the same branch entry from a prior update, the current branch is duplicated on every rerun.
Suggested fix
- if [[ -n "$new_change_entry" ]]; then
+ if [[ -n "$new_change_entry" ]] && ! grep -Fqx -- "$new_change_entry" "$target_file"; then
echo "$new_change_entry" >> "$temp_file"
fi📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| if [[ "$line" == "## Recent Changes" ]]; then | |
| echo "$line" >> "$temp_file" | |
| # Add new change entry right after the heading | |
| if [[ -n "$new_change_entry" ]]; then | |
| echo "$new_change_entry" >> "$temp_file" | |
| fi | |
| in_changes_section=true | |
| changes_entries_added=true | |
| continue | |
| elif [[ $in_changes_section == true ]] && [[ "$line" =~ ^##[[:space:]] ]]; then | |
| echo "$line" >> "$temp_file" | |
| in_changes_section=false | |
| continue | |
| elif [[ $in_changes_section == true ]] && [[ "$line" == "- "* ]]; then | |
| # Keep only first 2 existing changes | |
| if [[ $existing_changes_count -lt 2 ]]; then | |
| echo "$line" >> "$temp_file" | |
| ((existing_changes_count++)) | |
| fi | |
| if [[ "$line" == "## Recent Changes" ]]; then | |
| echo "$line" >> "$temp_file" | |
| # Add new change entry right after the heading | |
| if [[ -n "$new_change_entry" ]] && ! grep -Fqx -- "$new_change_entry" "$target_file"; then | |
| echo "$new_change_entry" >> "$temp_file" | |
| fi | |
| in_changes_section=true | |
| changes_entries_added=true | |
| continue | |
| elif [[ $in_changes_section == true ]] && [[ "$line" =~ ^##[[:space:]] ]]; then | |
| echo "$line" >> "$temp_file" | |
| in_changes_section=false | |
| continue | |
| elif [[ $in_changes_section == true ]] && [[ "$line" == "- "* ]]; then | |
| # Keep only first 2 existing changes | |
| if [[ $existing_changes_count -lt 2 ]]; then | |
| echo "$line" >> "$temp_file" | |
| ((existing_changes_count++)) | |
| fi |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.specify/scripts/bash/update-agent-context.sh around lines 465 - 483, The
Recent Changes block is not idempotent because the script always echoes
new_change_entry, causing duplicates; fix by detecting whether new_change_entry
already exists in that section before adding it: when you enter the "## Recent
Changes" branch (use the in_changes_section variable and the new_change_entry
variable), scan the following lines (until the next "## " heading) for a line
equal to new_change_entry and set a flag like new_change_present; only echo
new_change_entry into the temp_file if new_change_present is false, and ensure
existing_changes_count logic still copies at most two unique bullets (skip lines
equal to new_change_entry while counting) so reruns won't prepend a duplicate.
| **Branch**: `[###-feature-name]` | **Date**: [DATE] | **Spec**: [link] | ||
| **Input**: Feature specification from `/specs/[###-feature-name]/spec.md` | ||
|
|
||
| **Note**: This template is filled in by the `/speckit.plan` command. See `.specify/templates/plan-template.md` for the execution workflow. |
There was a problem hiding this comment.
Fix misleading self-reference in note.
This line points to the current file for execution workflow details. It should reference the command workflow document (e.g., .claude/commands/speckit.plan.md) instead.
📝 Proposed fix
-**Note**: This template is filled in by the `/speckit.plan` command. See `.specify/templates/plan-template.md` for the execution workflow.
+**Note**: This template is filled in by the `/speckit.plan` command. See `.claude/commands/speckit.plan.md` for the execution workflow.📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| **Note**: This template is filled in by the `/speckit.plan` command. See `.specify/templates/plan-template.md` for the execution workflow. | |
| **Note**: This template is filled in by the `/speckit.plan` command. See `.claude/commands/speckit.plan.md` for the execution workflow. |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.specify/templates/plan-template.md at line 6, Update the misleading
self-reference in the note: change the execution workflow link text in
.specify/templates/plan-template.md so it no longer points to the same template
but instead references the command workflow document (e.g.,
.claude/commands/speckit.plan.md) and the /speckit.plan command; edit the
sentence beginning "**Note**: This template is filled in by the `/speckit.plan`
command. See `.specify/templates/plan-template.md` for the execution workflow."
to point to the proper workflow doc (.claude/commands/speckit.plan.md) and
ensure the phrasing clearly ties the template to the `/speckit.plan` command.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
speckit.constitution.md(.specify/templates/commands/*.md→.claude/commands/speckit.*.md).repomap.txtto reflect new files added in PR Add spec-kit integration and rewrite spec-kit-auto skill #30.worktrees/to.gitignoreContext
Issues identified during code review of PR #30.
Depends on PR #30 being merged first (this branch is based on
feature/add-spec-kit-auto-skill).Test plan
speckit.constitution.mdreferences correct path.repomap.txtincludes new spec-kit files.worktrees/is gitignored🤖 Generated with Claude Code