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/ci-debug/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/ci-debug)<a href="https://agentmods.dev/skills/dancing-bear-show/dancing-bear/ci-debug"><img src="https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/ci-debug/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/ci-debug"><img src="https://agentmods.dev/badge/skills/dancing-bear-show/dancing-bear/ci-debug.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 | $0.00052 | $0.00894 |
| Opus 5.5 | $0.00021 | $0.00358 |
| Sonnet 5.5 | $0.00010 | $0.00179 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
ci-debug scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI Debug
Delegates to workflows/code/ci-debug.yaml.
When to Use
- User pastes a GitHub Actions run URL
- User says "CI is failing" or "fix CI"
- After a push when CI goes red
- As Phase 4 of
/review-fix
How to Run
IMPORTANT: Use the /workflow skill — do NOT call ./bin/workflow run --execute directly. It only writes dispatch files and exits (status=pending). The /workflow skill is what actually spawns agents, waits for results, and handles human gates.
# From a GitHub Actions run URL
Skill(skill="workflow", args="--workflow workflows/code/ci-debug.yaml --params run_url=<RUN_URL> test_cmd='PYTHONPATH=\"$PWD/src\" python3 -m unittest discover -s tests/<domain>_tests -t . -f -q' source_root='src/<domain>/'")
# From a PR number
Skill(skill="workflow", args="--workflow workflows/code/ci-debug.yaml --params pr_number=<PR_NUMBER> test_cmd='PYTHONPATH=\"$PWD/src\" python3 -m unittest discover -s tests/<domain>_tests -t . -f -q' source_root='src/<domain>/'")
# Both (run URL for logs + qlty PR-scoped check)
Skill(skill="workflow", args="--workflow workflows/code/ci-debug.yaml --params run_url=<RUN_URL> pr_number=<PR_NUMBER> test_cmd='PYTHONPATH=\"$PWD/src\" python3 -m unittest discover -s tests/<domain>_tests -t . -f -q' source_root='src/<domain>/'")
At least one of run_url or pr_number must be provided.
Workflow Params
| Param | Default | Description |
|---|---|---|
run_url |
"" |
GitHub Actions run URL (optional if pr_number given) |
pr_number |
"" |
PR number to check (optional if run_url given) |
test_cmd |
"" |
Test invocation for local verify (e.g. PYTHONPATH="$PWD/src" python3 -m unittest discover -s tests/core_tests -t . -f -q; -f is unittest's failfast — -x is pytest syntax and errors here. The PYTHONPATH prefix is required in a worktree or imports resolve to the main checkout.) |
source_root |
"" |
Source dir for coverage scoping (e.g. src/core/) |
min_coverage |
"80" |
Minimum new coverage % required by qlty gate |
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 · 59 lines · 52 tokens per session scan A 4a978b94fd88
ci-debug is a skill published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 894 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.
ci-debug compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ci-debugdancing-bear-show/dancing-bear | Skill | 7 | yesterday | MIT | A | 52 | Claude Code |
| atmos-lintcloudposse/atmos | Skill | 1.4k | today | Apache-2.0 | A | 64 | Claude Code |
| ci-fix-monitorZaxbyHub/opencode-swarm | Skill | 518 | today | MIT | A | 68 | Claude Code, Codex |
| swarm-ci-monitorZaxbyHub/opencode-swarm | Skill | 518 | today | MIT | A | 75 | Codex |
| diagnose-ci-failuresPyModel/pythinker-cli | Skill | 21 | 5d ago | Apache-2.0 | A | 31 | Claude Code, Codex |
| github-ci-fixpatrickserrano/lacquer | Skill | 5 | yesterday | MIT | A | 27 | Claude Code, Codex |
| ci-watchLucasSantana-Dev/sharekit | Skill | 2 | 6d ago | MIT | A | 55 | Claude Code |