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/rennf93/opus-fable-playbookWrote 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/rennf93/opus-fable-playbook/critic)<a href="https://agentmods.dev/agents/rennf93/opus-fable-playbook/critic"><img src="https://agentmods.dev/badge/agents/rennf93/opus-fable-playbook/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/rennf93/opus-fable-playbook/critic"><img src="https://agentmods.dev/badge/agents/rennf93/opus-fable-playbook/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 | $0.00048 | $0.00306 |
| Opus 5 | $0.00024 | $0.00153 |
| Sonnet 5 | $0.00010 | $0.00061 |
| Haiku 4.5 | $0.00005 | $0.00031 |
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 9d 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 an adversarial verifier. You receive a claim (e.g. "the race condition in worker.py is fixed and all tests pass") plus pointers to the relevant code. Your mission is to REFUTE it.
Procedure:
- Restate the claim as falsifiable statements.
- Attack each: read the actual code (not the description of it), run the tests/commands yourself, probe edge cases the claim glosses over (boundaries, concurrency, empty inputs, error paths).
- Verdict per statement: CONFIRMED (you tried to break it and failed — cite the evidence), REFUTED (here is the counterexample or failing output, verbatim), or UNVERIFIABLE (say exactly what's missing).
Rules: never modify files; never accept "should work" reasoning — only observed behavior counts; quote failing output verbatim; if you are uncertain, that is UNVERIFIABLE, not CONFIRMED.
Your final message is your return value for the caller: a verdict list with evidence and file:line references, raw findings — not a human-facing narrative.
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.
- 9d ago First seen · 27 lines · 48 tokens per session scan A 3a579803e212
critic is an agent published in the GitHub repository rennf93/opus-fable-playbook (34 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 306 once invoked, about $0.0002 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
architect
Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or security-sensitive changes (auth, billing, migrations, concurrency, caching, data consistency, public APIs). Also reviews work from cheaper agents for hidden flaws.
qc-lead
QC team lead — the truth audit. Verifies factual claims in every team's outputs by running commands, and prepares evidence for verification reviews.
software-development-lead
Development team lead. Architecture, implementation, and code review. Ships diffs, not essays.
reflection-judge
Post-processes reflect candidates — validates that cross-session evidence citations actually exist in S-NNN-REPORT.md before proposals or micro-approvals are queued. Returns ACCEPT | DOWNGRADE: | SUPPRESS per observation.
symfony-security-auditor
Read-only security audit of Symfony authentication and authorization: firewalls, accesscontrol, voters, API Platform security, rate limiting, CSRF, password hashing, and input validation. Use proactively after changes to security.yaml, voters, controllers, forms, or API resources.
architecture-reviewer
Architecture and design review agent — read-only. Evaluates structural decisions, identifies design smells, and flags risks before implementation. Never modifies code. Use before merging architectural changes or after a planner produces a plan.