Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add wan-huiyan/agent-review-panel --skill plan-review-integratorgit clone --depth 1 https://github.com/wan-huiyan/agent-review-panelWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wan-huiyan/agent-review-panel/plan-review-integrator)<a href="https://agentmods.dev/skills/wan-huiyan/agent-review-panel/plan-review-integrator"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-review-panel/plan-review-integrator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wan-huiyan/agent-review-panel/plan-review-integrator"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-review-panel/plan-review-integrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00197 | $0.06400 |
| Opus 5 | $0.00098 | $0.03200 |
| Sonnet 5 | $0.00039 | $0.01280 |
| Haiku 4.5 | $0.00020 | $0.00640 |
Grade A, and why
plan-review-integrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 515 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan-Review Integrator v2.0
Consumes structured review panel output and integrates findings into an implementation plan document -- turning review feedback into concrete plan updates with full traceability.
Key insight: Review panels often identify correct symptoms but prescribe wrong fixes when they lack domain context. Always validate recommendations against domain-specific constraints before applying them.
Quick Reference
| Stage | Phase | Action | Output |
|---|---|---|---|
| Gather | 1. Gather Inputs | Collect review reports + plan + domain context | Input set |
| 2. VoltAgent Detection | Detect specialists, suggest install if beneficial | Available specialist map | |
| Analyze | 3. Extract Findings | Parse findings with severity, source, citations | Structured finding list |
| 4. Cross-Reference | Match each finding against plan content | Category per finding | |
| 5. Actionability Filter | Score actionability, drop low-signal findings | Filtered finding list | |
| 6. Classify | Assign action category (epistemic-weighted) | must-fix / bundle / defer / info | |
| Apply | 7. Apply Edits | Edit plan document with rollback on coherence break | Updated plan |
| 8. Verify | Re-read modified plan, check coherence | Verified plan or rollback | |
| Finalize | 9. Update Peripherals | Update ADRs, runbooks, memory | Supporting docs |
| 10. Produce Summary | Traceability table | Audit trail | |
| 11. Persistent Log | Append decisions to integration log | integration_log.jsonl |
Phase 1: Gather Inputs
Collect three things:
- Review report(s) -- file path, inline paste, or reference to prior conversation
- Plan document -- markdown plan, design doc, RFC, or architecture proposal
- Domain context -- memory files, config files, related docs, session history
Domain context is essential for validating reviewer recommendations. Do NOT skip it.
Empty review guard: If the review contains no actionable findings (clean pass), produce no classifications and output: "No action items identified. Plan unchanged." Skip Phases 3-8 and go directly to Phase 10 with a summary confirming the clean review.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 515 lines · 197 tokens per session scan A 339041f8156a
plan-review-integrator is a skill published in the GitHub repository wan-huiyan/agent-review-panel (35 stars, last pushed 1mo ago), licensed MIT. It adds 197 tokens to every session and 6,400 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
deep-review
Multi-angle code review that adapts to what is being reviewed — a mid-flight worktree increment, a full PR before production, a merge-window integration sweep, or a security-only pass. Findings are scored, adversarially refuted, widened to the same defect elsewhere in the codebase, and reported to the native review…
codex-adversarial-review-lite
Codex Adversarial Review - Lite: user-invoked audit workflow for Claude Code users who want Codex CLI to independently review AI-generated code, plans, test expectations, and scope before fixes are applied. Cross-platform (Windows, macOS, Linux, WSL). Use only when the user explicitly invokes audit or selftest.
ads-linkedin
Audit LinkedIn Ads measurement, Insight Tag and conversions, professional audiences, lead generation, ABM, creative, bidding, budgets, pacing, automation, and policy. Use for LinkedIn Ads, Campaign Manager, Insight Tag, Lead Gen Forms, Thought Leader Ads, ABM campaigns, or B2B paid media.
ads-launch
Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters. Use for campaign creation, launch plans, publishing ads, activating campaigns, uploading creative, or requests to push a campaign live.
bun-test-mocking
Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.
api-response-optimization
Optimizes API performance through payload reduction, caching strategies, and compression techniques. Use when improving API response times, reducing bandwidth usage, or implementing efficient caching.