Plan Review
- 658 installs
- 1 repo stars
- Updated May 26, 2026
- camacho/ai-skills
plan-review is an agent skill that runs the PLAN checkpoint gate by auto-assembling reviewers from plan scope, dispatching parallel agent reviews, and blocking Build until every verdict is APPROVE.
About
plan-review is a phase-gate skill from camacho/ai-skills that implements the PLAN checkpoint in an agentic development workflow. It locates the latest non-done plan file under ai-workspace/plans/, deterministically assembles a review panel from plan scope, and dispatches reviewer agents in parallel to collect APPROVE or reject verdicts. Build cannot proceed until every reviewer—including the non-excludable technical-editor agent—returns APPROVE. Flags --include and --exclude let teams force-add or drop reviewers except technical-editor. Developers reach for plan-review when multi-agent plans need structured sign-off before code changes land, replacing informal plan chats with a blocking quality gate tied to concrete plan markdown files.
- PLAN checkpoint: MUST receive APPROVE from all reviewers before proceeding to Build
- Auto-finds latest non-.done.md plan under ai-workspace/plans/ with --include/--exclude panel overrides
- Invokes assemble-panel from file types and keywords; technical-editor cannot be excluded
- Dispatches selected agents in parallel in a single message; fallback panel [technical-editor, code-reviewer] gate P2 cap
- Errors when no plan exists or plan is already .done.md finalized
Plan Review by the numbers
- 658 all-time installs (skills.sh)
- Ranked #202 of 1,352 Code Review & Quality skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/camacho/ai-skills --skill plan-reviewAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 658 |
|---|---|
| repo stars | ★ 1 |
| Security audit | 3 / 3 scanners passed |
| Last updated | May 26, 2026 |
| Repository | camacho/ai-skills ↗ |
How do you gate agent builds behind plan approval?
Run the PLAN checkpoint gate that assembles reviewers from plan scope, dispatches agents in parallel, and blocks Build until every verdict is APPROVE.
Who is it for?
Teams using ai-workspace plan files who need deterministic multi-agent review before any Build phase starts.
Skip if: Repositories without ai-workspace/plans markdown plans or workflows that skip formal PLAN checkpoints.
When should I use this skill?
User finishes a plan file and needs PLAN checkpoint review, reviewer panel assembly, or Build blocked pending APPROVE verdicts.
What you get
Parallel reviewer verdicts, APPROVE-blocked Build gate, and audited plan-review record tied to the active plan markdown file.
- Reviewer verdict log
- APPROVE-gated Build checkpoint
- Assembled review panel record
By the numbers
- Reads plan files from ai-workspace/plans/ excluding .done.md archives
- technical-editor reviewer cannot be removed via --exclude
Files
Phase gate: PLAN checkpoint. MUST get APPROVE from all reviewers before proceeding to Build.
Inputs
- Plan file path (default: most recent non-
.done.mdfile inai-workspace/plans/) --include <agent>: Force-add an agent to the panel--exclude <agent>: Remove an agent (except technical-editor, which cannot be excluded)
Steps
1. Find the plan file:
ls -t "$(git rev-parse --show-toplevel)/ai-workspace/plans/"*.md | grep -v '.done.md' | head -1If no plan file found → error: "No plan file in ai-workspace/plans/. Write a plan first." If plan file is .done.md → error: "This plan is already finalized."
2. Read the plan and extract:
- Files to Modify section
- Full body text
- Plan scope (count files changed, count body lines)
3. Assemble the review panel — invoke /assemble-panel with scope = plan file. It returns the panel based on file types and keywords in the plan. Pass --include/--exclude as overrides. Log which agents were selected and why.
Codex/Cursor: read .claude/skills/assemble-panel/SKILL.md directly and apply the scope/keyword maps inline.
If /assemble-panel is unavailable, fall back to [technical-editor, code-reviewer] with gate=P2, cap=3.
4. Dispatch all selected agents IN PARALLEL using the Agent tool (single message, multiple Agent tool calls). Each agent receives:
- The plan file content
- Their specific review mandate
- Instructions to return: APPROVE / REVISE / DROP with findings tagged P0/P1/P2
5. Collect verdicts and synthesize into a summary table:
## Plan Review Summary
| Agent | Verdict | P0 | P1 | P2 | Key Finding |
|-------|---------|----|----|-----|-------------|6. Gate logic and review loop — invoke /assemble-panel for panel governance. It provides the policy algebra (gate=P2, cap=3) and handles RETAIN, EXPAND, CONVERGE, and ESCALATE_RECURRING. Do not duplicate those rules here.
After each round:
- All APPROVE with no above-gate findings → "Proceed to Build"
- Above-gate findings remain → fix, then re-review per assemble-panel's RETAIN + EXPAND rules
- Cap reached with unresolved findings → escalate to human
If /assemble-panel is unavailable, fall back: keep all reviewers with above-gate findings, exit at round 3 or when all clean.
Panel Bounds
- Minimum: technical-editor alone (1 agent, trivial plans)
- Typical: technical-editor + code-reviewer + architect-reviewer (3)
- Maximum: all agents (rare, large cross-cutting plans)
Related skills
Improve Codebase ArchitectureSafely deepen clusters of shallow modules into cohesive, testable units while respecting their external dependencies.566k196k
Caveman ReviewGet ultra-compressed, one-line code review comments that cut noise while keeping every actionable fix.270k94.7kCodebase DesignShared vocabulary for designing deep modules: improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable.266k196kCavecrewDelegate coding tasks to specialized subagents that return compressed output, keeping the main context window usable for much longer sessions.220k94.7kCode ReviewReviews a branch or PR diff on two axes at once: conformance to coding standards plus a code-smell baseline, and whether it actually implements the original spec.201k196k
Requesting Code ReviewDispatch a consistent, high-signal code reviewer subagent that catches plan deviations and quality issues before merging or continuing development.183k264kHow it compares
Use this over ad-hoc code review skills when the workflow requires a formal PLAN gate with parallel agent verdicts before implementation.
FAQ
What file does plan-review read by default?
plan-review reads the most recent non-.done.md file in ai-workspace/plans/ at the git repository root. If no plan file exists, the skill errors and stops before dispatching reviewers.
Can plan-review proceed without unanimous approval?
plan-review blocks the Build phase until every assembled reviewer, including the mandatory technical-editor agent, returns an APPROVE verdict. Any missing approval prevents Build from starting.
Is Plan Review safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.