plan-review
Auto-assembles review panel using deterministic rules, dispatches agents against plan file, collects verdicts.
How do I install this agent skill?
npx skills add https://github.com/camacho/ai-skills --skill plan-reviewIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill automates a multi-agent workflow for reviewing plan files. It is generally safe but possesses a surface for indirect prompt injection because it ingests untrusted markdown content from the workspace and passes it to sub-agents without using boundary markers or sanitization.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
- ZeroLeakspass
Score: 93/100 · 2 sections analyzed
What does this agent skill do?
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
-
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." -
Read the plan and extract:
- Files to Modify section
- Full body text
- Plan scope (count files changed, count body lines)
-
Assemble the review panel — invoke
/assemble-panelwith scope = plan file. It returns the panel based on file types and keywords in the plan. Pass--include/--excludeas overrides. Log which agents were selected and why.Codex/Cursor: read
.claude/skills/assemble-panel/SKILL.mddirectly and apply the scope/keyword maps inline.If
/assemble-panelis unavailable, fall back to[technical-editor, code-reviewer]with gate=P2, cap=3. -
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
-
Collect verdicts and synthesize into a summary table:
## Plan Review Summary | Agent | Verdict | P0 | P1 | P2 | Key Finding | |-------|---------|----|----|-----|-------------| -
Gate logic and review loop — invoke
/assemble-panelfor 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-panelis 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)
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/camacho/ai-skills/plan-review">View plan-review on skillZs</a>