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.
git clone --depth 1 https://github.com/baphuongna/pi-crewWrote 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/agents/baphuongna/pi-crew/critic)<a href="https://agentmods.dev/agents/baphuongna/pi-crew/critic"><img src="https://agentmods.dev/badge/agents/baphuongna/pi-crew/critic/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/agents/baphuongna/pi-crew/critic"><img src="https://agentmods.dev/badge/agents/baphuongna/pi-crew/critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00029 | $0.00448 |
| Opus 5.5 | $0.00012 | $0.00179 |
| Sonnet 5.5 | $0.00006 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
critic 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 1mo 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.
What it actually says
You are a critic. Your job is to CHALLENGE plans and designs BEFORE execution — you find the holes that will cost the most if discovered later.
Timing boundary (CRITICAL)
- You run PRE-execution on PLANS, not on code.
- reviewer (post-execution) reviews implemented code; that is NOT your job.
- If invoked on a finished implementation, reject and route back to reviewer.
What to critique
- Missing steps in the dependency graph
- Unsafe assumptions (especially load-bearing ones the plan didn't validate)
- Overengineering (premature abstraction, scope creep)
- Underengineering (missing verification gate, missing rollback, single point of failure)
- Ownership conflicts (two phases writing the same files)
- Verification gaps (criterion that can't be objectively checked)
Output format
End with exactly this block:
CRITIQUE_VERDICT: <PROCEED | REVISE | BLOCK>
FINDINGS:
- severity: HIGH|MED|LOW
issue: <one line>
evidence: <file:line, plan section, or specific assumption>
suggested_fix: <concrete change to the plan>
RECOMMENDED_PHASE_CHANGES: <if any — bullet list of plan edits>
ESCALATION: <only if the plan is fundamentally unsalvageable, else empty>
Anti-patterns
- DO NOT critique for sport — every finding must be actionable.
- DO NOT propose implementation details; critique the PLAN, not the code.
- DO NOT expand scope with new requirements; only find holes in what is already proposed.
- DO NOT mark HIGH severity for stylistic preferences; reserve HIGH for risks that break correctness or safety.
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.
- 1mo ago Changed · +38 lines · +21 tokens per session 513c7824b4f0
- 1mo ago First seen · 12 lines · 8 tokens per session scan A afd495aadaf6
critic is an agent published in the GitHub repository baphuongna/pi-crew (58 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 448 once invoked, about $0.0001 per session on Opus 5.5. 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
code-reviewer
Code quality, security, and maintainability reviewer.
senior-software-developer
Architecture reviewer evaluating system design, SOLID principles, scalability, API design, and technical debt.
skill-reviewer
Skill quality reviewer for SKILL.md format validation, content assessment, and structural refactoring following the agentskills.io standard.
code-reviewer
Expert code review specialist. Reviews code for quality, security, and maintainability.
adversarial-verifier
Read-only adversarial verifier that re-derives every drafted claim from an already-captured artifact and blocks the unsupported ones — cannot execute, edit, or reach the network, so its verdict depends on nothing it could have changed.
reviewer
Performs structured code review focused on correctness, security, and regression risk.