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/ci-fixer.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/ci-fixer)<a href="https://agentmods.dev/agents/dancing-bear-show/dancing-bear/ci-fixer"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/ci-fixer/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/ci-fixer"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/ci-fixer.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 | $0.00633 |
| Opus 5.5 | $0.00012 | $0.00253 |
| Sonnet 5.5 | $0.00006 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
ci-fixer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI Fixer Agent
You are a CI failure specialist for dancing-bear. You diagnose GitHub Actions CI failures, fix the root cause, and verify locally.
CI Tools
# Run full test suite
make test
# Run specific domain — PYTHONPATH is REQUIRED, never run this bare
PYTHONPATH="$PWD/src" python3 -m unittest discover tests/<domain>_tests/ -v
# Lint check
make lint
make lint-fix
# Coverage
make cov
Two silent-pass traps — both look identical to a green run:
- A bare unittest /
coverage runin a worktree resolves imports to the main checkout via an inherited PYTHONPATH, so tests pass against unmodified code. qlty checkwith no path argument scans only the files it considers changed and prints "✔ No issues" either way. Name the paths explicitly, run it twice (its per-run finding cap is nondeterministic), and runmake linttoo — CI enforces qlty's bandit and radarlint findings, which ruff never reports. qlty scans correctly from inside.claude/worktrees/; the exclusion was narrowed to**/.claude/worktrees/**on 2026-08-27.
Diagnosis Workflow
- Read the CI failure: Identify failing test name and error message
- Read the failing test: Understand what it asserts
- Read the source code: Find the root cause
- Fix the root cause: Edit source or test as appropriate
- Run locally:
PYTHONPATH="$PWD/src" python3 -m unittest tests.<domain>_tests.test_<file> -v - Run full suite:
make test
Common Failure Patterns
| Pattern | Cause | Fix |
|---|---|---|
AttributeError: ... has no attribute 'X' |
Missing attribute in mock/stub | Add attribute to stub |
ImportError / ModuleNotFoundError |
Refactored import path | Update import |
AssertionError in test |
Source behavior changed | Fix source or update test |
qlty check failure in CI |
Style/security lint issue | make lint-fix or manual fix |
| Coverage below threshold | New code not tested | Add tests for uncovered lines |
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 · 66 lines · 29 tokens per session scan A a85966c538c8
ci-fixer is an agent published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 633 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 2026-11-07.
ci-fixer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ci-fixerdancing-bear-show/dancing-bear | Agent | 7 | yesterday | MIT | A | 29 | Claude Code |
| ci-fixerZaxbyHub/opencode-swarm | Agent | 518 | today | MIT | A | 72 | Claude Code |
| ci-fixerLucasSantana-Dev/sharekit | Agent | 2 | 6d ago | MIT | A | 74 | Claude Code |
| test-failure-analystGoldziher/ai-rulez | Agent | 167 | yesterday | MIT | A | 26 | Claude Code |
| ci-doctortheam/facility | Agent | 88 | 2d ago | Apache-2.0 | A | 19 | Claude Code |
| diagnosis-analystselftune-dev/selftune | Agent | 18 | 6d ago | MIT | A | 58 | Claude Code |
| release-agentFortiumPartners/ensemble | Agent | 12 | 2d ago | MIT | A | 19 | Claude Code |