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/skills/review-and-fix/SKILL.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/skills/dancing-bear-show/dancing-bear/review-and-fix)<a href="https://agentmods.dev/skills/dancing-bear-show/dancing-bear/review-and-fix"><img src="https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/review-and-fix/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/dancing-bear-show/dancing-bear/review-and-fix"><img src="https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/review-and-fix.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 | $0.00043 | $0.01348 |
| Opus 5.5 | $0.00017 | $0.00539 |
| Sonnet 5.5 | $0.00009 | $0.00270 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
review-and-fix 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review and Fix
Delegates to workflows/code/review-and-fix.yaml. Phase 1 runs the adversarial swarm review
(diff fetch, concern sweep, per-file validation, consolidation, fact-check, human gate,
inline comment posting). Phase 2 triages findings by fix type, fans out code, test, and
qlty fixes in parallel, verifies everything is green, resolves posted threads, and
presents a summary for final approval.
When to Use
- User says "review and fix", "swarm fix", or "review then auto-fix"
- One-shot review + remediation before merge
- Existing review findings need automated fixing (set
skip_review: "true")
Derive Params from Context
# Detect PR number from current branch
GITHUB_TOKEN= gh pr view --json number -q .number
If the command returns a number, use it. If the branch has no open PR, ask the user.
Invocation
IMPORTANT: Use the /workflow skill — do NOT call ./bin/workflow run --execute directly. It only writes dispatch files and exits (status=pending). The /workflow skill is what actually spawns agents, waits for results, and handles human gates.
Skill(skill="workflow", args="--workflow workflows/code/review-and-fix.yaml --params pr_number=314 test_cmd='PYTHONPATH=\"$PWD/src\" python3 -m unittest discover -s tests/mail_tests -t . -f -q' source_root=src/mail/ test_path=tests/mail_tests/")
Skip Phase 1 if review already ran and findings are in /tmp/review-and-fix-{pr_number}/outputs/:
Skill(skill="workflow", args="--workflow workflows/code/review-and-fix.yaml --params pr_number=314 skip_review=true")
Params
| Param | Default | Description |
|---|---|---|
pr_number |
"" |
PR number (required; auto-detected from branch if blank) |
test_cmd |
"" |
e.g. PYTHONPATH="$PWD/src" python3 -m unittest discover -s tests/mail_tests -t . -f -q |
source_root |
"" |
e.g. src/mail/ |
test_path |
"" |
e.g. tests/mail_tests/ |
min_coverage |
"80" |
Coverage threshold (percent, no % sign) |
auth_domains |
"github,qlty" |
Auth domains to pre-check |
skip_review |
"false" |
Set "true" to jump straight to Phase 2 |
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 · 92 lines · 43 tokens per session scan A fe4cb22a46f9
review-and-fix is a skill published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,348 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.
review-and-fix compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| review-and-fixdancing-bear-show/dancing-bear | Skill | 7 | yesterday | MIT | A | 43 | Claude Code |
| autofix-prQwenLM/qwen-code | Skill | 29k | today | Apache-2.0 | A | 141 | Claude Code |
| gh-find-prsHmbown/CodeWhale | Skill | 41k | today | MIT | A | 27 | Claude Code, Codex |
| hunk-releasemodem-dev/hunk | Skill | 9.8k | yesterday | MIT | A | 38 | Claude Code, Codex |
| gitx-cmd/x-cmd | Skill | 4.7k | 8d ago | Apache-2.0 | A | 58 | Claude Code, Codex |
| vhs-e2e-gifdimetron/pi-go | Skill | 223 | today | MIT | A | 106 | Claude Code, Codex |
| agent-debug-ciNVIDIA/elements | Skill | 115 | yesterday | Apache-2.0 | A | 80 | Claude Code, Codex |