Agent skill
feature-plan
Generate EXECUTION_PLAN.md and AGENTS_ADDITIONS.md for a feature. Use after /feature-technical-spec to create the task breakdown.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/feature-plan-benjaminshoemaker-ai-coding-project-ba
SKILL.md
Generate the execution plan and agent additions for the feature $1.
Workflow
Copy this checklist and track progress:
Feature Plan Progress:
- [ ] Directory guard
- [ ] Handle arguments (feature name)
- [ ] Check prerequisites (FEATURE_SPEC.md + FEATURE_TECHNICAL_SPEC.md)
- [ ] Existing file guard (prevent overwrite)
- [ ] Generate EXECUTION_PLAN.md and AGENTS_ADDITIONS.md
- [ ] Verify execution skills installed
- [ ] Codex CLI detection and skill install
- [ ] Run spec-verification
- [ ] Run criteria audit
- [ ] Cross-model review (if Codex available)
Directory Guard
-
If
START_PROMPTS.mdorGENERATOR_PROMPT.mdexists in the current working directory → STOP: "You're in the toolkit repo. Feature skills run from your project directory. Run:cd ~/Projects/your-project && /feature-plan $1" -
Check
.claude/toolkit-version.jsonexists in the current working directory (confirms/setupwas run). If missing → STOP: "Toolkit not installed. Run/setupfrom the toolkit first." -
Check
AGENTS.mdexists in the current working directory (confirms project root). If missing → STOP: "Run this from your project root (where AGENTS.md lives)."
Arguments
$1= feature name (e.g.,analytics,dark-mode)- If
$1is empty, ask the user for the feature name PROJECT_ROOT= current working directoryFEATURE_DIR=PROJECT_ROOT/features/$1
Prerequisites
- Check that
FEATURE_DIR/FEATURE_SPEC.mdexists. If not: "FEATURE_SPEC.md not found at features/$1/. Run/feature-spec $1first." - Check that
FEATURE_DIR/FEATURE_TECHNICAL_SPEC.mdexists. If not: "FEATURE_TECHNICAL_SPEC.md not found at features/$1/. Run/feature-technical-spec $1first." - Check that
PROJECT_ROOT/AGENTS.mdexists. If not: "AGENTS.md not found. Feature development requires an existing AGENTS.md."
Existing File Guard (Prevent Overwrite)
Before generating anything, check whether either output file already exists:
-
FEATURE_DIR/EXECUTION_PLAN.md -
FEATURE_DIR/AGENTS_ADDITIONS.md -
If neither exists: continue normally.
-
If one or both exist: STOP and ask the user what to do for the existing file(s):
- Backup then overwrite (recommended): for each existing file, read it and write it to
{path}.bak.YYYYMMDD-HHMMSS, then write the new document(s) to the original path(s) - Overwrite: replace the existing file(s) with the new document(s)
- Abort: do not write anything; suggest they rename/move the existing file(s) first
- Backup then overwrite (recommended): for each existing file, read it and write it to
Process
Read .claude/skills/feature-plan/PROMPT.md and follow its instructions exactly:
- Read
FEATURE_DIR/FEATURE_SPEC.mdandFEATURE_DIR/FEATURE_TECHNICAL_SPEC.mdas inputs - Read existing
PROJECT_ROOT/AGENTS.mdto understand current conventions - Generate EXECUTION_PLAN.md with phases, steps, and tasks for the feature
- Generate AGENTS_ADDITIONS.md with any additional workflow guidelines
Output
Write both documents to the feature directory:
FEATURE_DIR/EXECUTION_PLAN.mdFEATURE_DIR/AGENTS_ADDITIONS.md
Verify Execution Skills
After writing the documents, verify the execution skills are available so /fresh-start, /phase-start, etc. work from the feature directory.
Check if .claude/skills/fresh-start/SKILL.md exists in PROJECT_ROOT:
- If it exists: good — execution skills are installed
- If it does not exist: STOP and tell the user:
"Execution skills are missing. Run
/setupfrom the toolkit to install them."
Codex CLI Detection (Always Runs)
Check if OpenAI Codex CLI is installed:
command -v codex >/dev/null 2>&1
If Codex is NOT detected: skip silently.
If Codex IS detected:
-
Check for new skills by comparing toolkit skills to installed skills:
bash# Get installed skills INSTALLED_SKILLS=$(ls ~/.codex/skills/ 2>/dev/null | grep -v '^\.') -
If no installed skills exist (first time), use AskUserQuestion:
Question: "Codex CLI detected. Install toolkit skills for Codex?" Options: - "Yes, install" — Install skills via symlink (auto-updates with toolkit) - "No, skip" — Don't install Codex skills -
If user selects install, resolve toolkit location from
.claude/toolkit-version.json:bashTOOLKIT_PATH=$(jq -r '.toolkit_location' .claude/toolkit-version.json) "$TOOLKIT_PATH/scripts/install-codex-skill-pack.sh" --method symlink -
Report installation result.
Verification (Automatic)
After writing EXECUTION_PLAN.md, run the spec-verification workflow:
- Read
.claude/skills/spec-verification/SKILL.mdfor the verification process - Verify context preservation: Check that all key items from FEATURE_TECHNICAL_SPEC.md and FEATURE_SPEC.md appear as tasks or acceptance criteria
- Run quality checks for untestable criteria, missing dependencies, vague language, regression coverage
- Present any CRITICAL issues to the user with resolution options
- Apply fixes based on user choices
- Re-verify until clean or max iterations reached
IMPORTANT: Do not proceed to "Next Step" until verification passes or user explicitly chooses to proceed with noted issues.
Criteria Audit
Run /criteria-audit FEATURE_DIR to validate verification metadata in EXECUTION_PLAN.md.
This passes the feature directory so criteria-audit reads features/$1/EXECUTION_PLAN.md
instead of looking in the project root.
- If FAIL: stop and ask the user to resolve missing metadata before proceeding.
- If WARN: report and continue.
Cross-Model Review (Automatic)
After verification passes, run cross-model review if Codex CLI is available:
- Check if Codex CLI is installed:
codex --version - If available, run
/codex-consultwith upstream context - Present any findings to the user before proceeding
Consultation invocation:
/codex-consult --upstream features/$1/FEATURE_TECHNICAL_SPEC.md --research "execution planning, task breakdown" features/$1/EXECUTION_PLAN.md
If Codex finds issues:
- Show critical issues and recommendations
- Ask user: "Address findings before proceeding?" (Yes/No)
- If Yes: Apply suggested fixes
- If No: Continue with noted issues
If Codex unavailable: Skip silently and proceed to Next Step.
Next Step
When verification is complete, inform the user:
EXECUTION_PLAN.md and AGENTS_ADDITIONS.md created and verified at features/$1/
Verification: PASSED | PASSED WITH NOTES | NEEDS REVIEW
Cross-Model Review: PASSED | PASSED WITH NOTES | SKIPPED
Next steps:
1. /fresh-start (will offer to merge AGENTS_ADDITIONS.md if needed)
2. /configure-verification
3. /phase-prep 1
4. /phase-start 1
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?