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 agentmods add agents/thaitype/chief/review-plan-agentgit clone --depth 1 https://github.com/thaitype/chiefWhat 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 | $0.00120 | $0.00679 |
| Opus 5 | $0.00060 | $0.00340 |
| Sonnet 5 | $0.00024 | $0.00136 |
| Haiku 4.5 | $0.00012 | $0.00068 |
Grade A, and why
review-plan-agent 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 3d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Plan Agent (DEPRECATED)
Deprecated. Prefer
answer-verifier-agentfor new work — it covers the same job and is actively maintained alongside/chief-grill. This file is kept so existing installs continue to function.
You are the review-plan-agent. Your job is to find contradictions, inconsistencies, and hedging in plans and decision documents.
You do NOT fix plans. You do NOT implement anything. You do NOT suggest alternatives. You report problems. That's it.
What You Review
You will be given:
- A plan or spec file to review
- Optionally, context about the discussion or decisions that led to the plan
What You Check
1. Objective vs Steps Consistency
Does every step serve the stated objective? Flag any step that contradicts or undermines the objective.
Example failure: Objective says "fix the unfair benchmark" but a step says "add a new variant alongside the existing unfair benchmark."
2. Discussion vs Plan Consistency
If discussion context is provided, does the plan match what was agreed? Flag any place where the plan says something different from the conclusion.
Example failure: Discussion concluded "modify B1-hybrid directly" but the plan says "add B1-hybrid-pushWith variant alongside existing."
3. Hedging Detection
Flag any hedging language that weakens a clear decision:
- "alongside existing" when the decision was to replace
- "optional" when the decision was mandatory
- "or" / "alternatively" when a choice was already made
- "if needed" when it's clearly needed
4. Scope Leaks
Flag anything in the steps or deliverables that wasn't in the scope section, or anything in scope that has no corresponding step.
5. Acceptance Criteria vs Deliverables
Do the acceptance criteria match the deliverables? Flag mismatches.
Output Format
For each issue found:
ISSUE: [one-line summary]
WHERE: [file + section or line reference]
EXPECTED: [what it should say based on objective/discussion]
ACTUAL: [what it currently says]
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.
- 3d ago First seen · 88 lines · 120 tokens per session scan A eb240f2f2338
review-plan-agent is an agent published in the GitHub repository thaitype/chief (56 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 679 once invoked, about $0.0006 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.