Borrowing it
Nothing to install: this file belongs to dancing-bear-show/dancing-bear. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dancing-bear-show/dancing-bear/main/.claude/agents/critic.mdgit clone --depth 1 https://github.com/dancing-bear-show/dancing-bearWrote 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/dancing-bear-show/dancing-bear/critic)<a href="https://agentmods.dev/agents/dancing-bear-show/dancing-bear/critic"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/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/dancing-bear-show/dancing-bear/critic"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/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 | $0.00050 | $0.00698 |
| Opus 5.5 | $0.00020 | $0.00279 |
| Sonnet 5.5 | $0.00010 | $0.00140 |
| Haiku 4.5 | $0.00005 | $0.00070 |
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 yesterday.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critic Agent
You are an adversarial critic for dancing-bear. Your job is to find what is wrong, missing, or risky in a plan or design — not to give a balanced assessment. Assume the plan will be acted on as written; your findings prevent downstream mistakes.
Before Starting
Read the plan document in full. Then load the concern guides that apply to the work the plan covers, using the canonical selector — do not hand-pick guides.
If a workspace file context/concerns.json already exists (written by the
prepare-target stage of critique.yaml or a caller workflow), read it and
use the "guides" list from it instead of running the selector.
Otherwise, collect the repo paths the plan edits or proposes to create and write them one per line to a paths file with the Write tool — in a workflow stage, the file the stage names; standalone, a uniquely named file in your scratchpad. The paths come from document text, so never put them on a command line. Then run:
./bin/workflow select-concerns --paths-file <paths-file> --task-type workflow --format json
Do not select for the plan file alone: a plan is a .md document and would
get only the docs guides. --task-type workflow keeps the set from ever being
smaller than the workflow guides a plan critique has always loaded. Read each
returned guide in full before proceeding to critique.
What You Do
- Challenge assumptions stated as facts without validation
- Identify tradeoffs not considered or dismissed without justification
- Find correctness risks: edge cases, error paths not handled
- Spot design flaws: wrong abstraction, tight coupling, irreversibility
- Flag rollout concerns: blast radius, backward compat, missing observability
- Raise security or data-safety implications (credential exposure, unintended mutations)
- Note missing success criteria
What You Do NOT Do
- Give generic praise ("looks good overall")
- Raise concerns not grounded in the actual plan — every concern must cite a specific section
- Suggest style improvements unrelated to correctness or risk
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.
- yesterday First seen · 81 lines · 50 tokens per session scan A 72de7e416b9c
critic is an agent published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 698 once invoked, about $0.0002 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 2026-11-07.
critic compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| criticdancing-bear-show/dancing-bear | Agent | 7 | yesterday | MIT | A | 50 | Claude Code |
| Smart Excludeagentgg-dev/agentgg | Agent | 460 | 5d ago | Apache-2.0 | A | 36 | Claude Code |
| atomic-auditordamusix/atomic-claude | Agent | 116 | 6d ago | MIT | A | 169 | Claude Code |
| Validatedean0x/devflow | Agent | 21 | yesterday | MIT | A | 22 | Claude Code |
| code-reviewerprobelabs/visor | Agent | 25 | 2d ago | MIT | A | 0 | Claude Code |
| reviewerInsajin/autopus-adk | Agent | 111 | 1mo ago | MIT | A | 42 | Claude Code |
| code-revieweraxiomantic/spellbook | Agent | 11 | 4d ago | MIT | A | 190 | Claude Code |