Validate Plan
SkillDev toolsValidate that an implementation plan was correctly executed by
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Validate Plan skill
What this skill tells your AI
The instructions your AI receives, as published by atomicinnovation/accelerator in skills/planning/validate-plan/SKILL.md and read by ahel’s review.
!${CLAUDE_PLUGIN_ROOT}/bin/accelerator config context --skill validate-plan --fail-safe
!${CLAUDE_PLUGIN_ROOT}/bin/accelerator config agents --fail-safe
If no "Agent Names" section appears above, use these defaults: accelerator:reviewer, accelerator:codebase-locator, accelerator:codebase-analyser, accelerator:codebase-pattern-finder, accelerator:documents-locator, accelerator:documents-analyser, accelerator:web-search-researcher.
Plans directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path plans --fail-safe
Validations directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path validations --fail-safe
Plan Validation Template
The template below defines the frontmatter and body structure that every plan validation report must carry. Read it now — use it to guide what information you record in the validation process and what shape you persist in Step 4.
!${CLAUDE_PLUGIN_ROOT}/bin/accelerator config template validation --fail-safe
You are tasked with validating that an implementation plan was correctly executed, verifying all success criteria and identifying any deviations or issues.
Initial Setup
When invoked:
- Determine context - Are you in an existing conversation or starting fresh?
- If existing: Review what was implemented in this session
- If fresh: Need to discover what was done through git and codebase analysis
- Locate the plan:
- If plan path provided, use it
- Otherwise, search recent commits for plan references or ask user
- Gather implementation evidence:
# Check recent commits git log --oneline -n 20 git diff HEAD~N..HEAD # Where N covers implementation commits # Run comprehensive checks cd $(git rev-parse --show-toplevel) && make check test
Validation Process
Step 1: Context Discovery
If starting fresh or need more context:
- Read the implementation plan completely
- Identify what should have changed:
- List all files that should be modified
- Note all success criteria (automated and manual)
- Identify key functionality to verify
- Spawn parallel research tasks to discover implementation:
Task 1 - Verify database changes: Research if migration [N] was added and schema changes match plan. Check: migration files, schema version, table structure Return: What was implemented vs what plan specified Task 2 - Verify code changes: Find all modified files related to [feature]. Compare actual changes to plan specifications. Return: File-by-file comparison of planned vs actual Task 3 - Verify test coverage: Check if tests were added/modified as specified. Run test commands and capture results. Return: Test status and any missing coverage
Step 2: Systematic Validation
For each phase in the plan:
- Check completion status:
- Look for checkmarks in the plan (- [x])
- Verify the actual code matches claimed completion
- Run automated verification:
- Execute each command from "Automated Verification"
- Document pass/fail status
- If failures, investigate root cause
- Assess manual criteria:
- List what needs manual testing
- Provide clear steps for user verification
- Think deeply about edge cases:
- Were error conditions handled?
- Are there missing validations?
- Could the implementation break existing functionality?
Step 3: Generate Validation Report
Compose the validation report body following the structure defined in the Plan Validation Template at the top of this skill (Implementation Status, Automated Verification Results, Code Review Findings, Manual Testing Required, Recommendations).
Step 4: Persist the Validation Report
Write the validation report to the configured validations directory:
-
Derive the filename from the plan filename: extract the filename stem (without directory path or
.mdextension) regardless of how the path was provided. For example, if the plan is{plans directory}/2026-03-22-improve-error-handling.md, the validation is{validations directory}/2026-03-22-improve-error-handling-validation.md. -
Create the configured validations directory if it doesn't exist.
Populate frontmatter
The target: field is filled automatically from the plan reference under
validation — this is what makes the report traceable back to the plan it
covers. Per ADR-0034, the typed-linkage form is "plan:<plan-id>".
Before writing the validation file, capture metadata and substitute the unified base fields and per-type extras into the template's frontmatter block:
- Invoke
${CLAUDE_PLUGIN_ROOT}/bin/accelerator corpus metadata deriveto obtainCurrent Date/Time (UTC):. - Substitute every field below with the indicated value:
type:←plan-validationid:← the validation filename stem (e.g.2026-05-30-0065-update-artifact-templates-to-unified-schema-validation), always quoted as a YAML stringtitle:←Validation Report: {plan title}date:← theCurrent Date/Time (UTC):valueauthor:← the author value resolved percreate-work-item/SKILL.md:578-580producer:←validate-planstatus:←completelast_updated:← the sameCurrent Date/Time (UTC):valuelast_updated_by:← the same value resolved forauthorschema_version:←1(bare integer, not quoted)parent:← typed-linkage ref to the parent plan ("plan:NNNN"). Fill when the validation names a parent plan; otherwise omit the key.target:←"plan:<plan-id>"(e.g."plan:2026-05-30-0065-update-artifact-templates-to-unified-schema"); the typed-linkage ref to the plan being validated, per ADR-0034. Always fill — every validation has a target.relates_to:← list of typed-linkage refs to related artifacts (["plan-validation:NNNN", ...]). Fill when related validations are explicit; otherwise omit the key.result:←pass | partial | failper the Implementation Status of the report (see derivation rule below)
- Write the file with the substituted frontmatter block followed by the validation report body from Step 3.
Determine the result field from the report:
pass: all phases fully implemented, all automated checks passpartial: some phases implemented or some checks failingfail: major deviations or critical failures
-
If the validation result is
pass, update the plan's frontmatterstatusfield todone(if the plan has YAML frontmatter with astatusfield). This closes the plan lifecycle. -
Inform the user where the report was saved:
Validation report saved to {validations directory}/{filename}.md
Validate the frontmatter: after writing, run corpus frontmatter validate over the validation report you just wrote:
${CLAUDE_PLUGIN_ROOT}/bin/accelerator corpus frontmatter validate --file <path>
If it exits non-zero, the report violates the canonical frontmatter standard; report the emitted violation and fix the frontmatter before completing.
Working with Existing Context
If you were part of the implementation:
- Review the conversation history
- Check your todo list for what was completed
- Focus validation on work done in this session
- Be honest about any shortcuts or incomplete items
Important Guidelines
- Be thorough but practical - Focus on what matters
- Run all automated checks - Don't skip verification commands
- Document everything - Both successes and issues
- Think critically - Question if the implementation truly solves the problem
- Consider maintenance - Will this be maintainable long-term?
Validation Checklist
Always verify:
- All phases marked complete are actually done
- Automated tests pass
- Code follows existing patterns
- No regressions introduced
- Error handling is robust
- Documentation updated if needed
- Manual test steps are clear
Relationship to Other Commands
Recommended workflow:
/implement-plan- Execute the implementation/commit- Create atomic commits for changes/validate-plan- Verify implementation correctness (saves report to the configured validations directory)/describe-pr- Generate PR description
The validation works best after commits are made, as it can analyze the git history to understand what was implemented.
Remember: Good validation catches issues before they reach production. Be constructive but thorough in identifying gaps or improvements.
!${CLAUDE_PLUGIN_ROOT}/bin/accelerator config instructions validate-plan --fail-safe
Signals
- GitHub stars
- 31
- Forks
- 1
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
validate-plan- Source
- github.com/atomicinnovation/accelerator