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.
npx skills add lfyxhappy/lfcode --skill ci-debuggergit clone --depth 1 https://github.com/lfyxhappy/lfcodeWrote 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/lfyxhappy/lfcode/ci-debugger)<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/ci-debugger"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/ci-debugger/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/lfyxhappy/lfcode/ci-debugger"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/ci-debugger.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 | $0.00085 | $0.00331 |
| Opus 5.5 | $0.00034 | $0.00132 |
| Sonnet 5.5 | $0.00017 | $0.00066 |
| Haiku 4.5 | $0.00009 | $0.00033 |
Grade A, and why
ci-debugger 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 1mo 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
CI Debugger
Reduce a failed pipeline to its first actionable cause and verify the narrowest repair.
Workflow
- Identify the pipeline, revision, job, platform, first failing step, and whether the failure is deterministic, flaky, or infrastructure-related.
- Read workflow configuration, task scripts, lockfiles, environment assumptions, artifact paths, and relevant logs with sensitive values redacted.
- Reproduce locally or in the closest safe environment using the same command, runtime version, inputs, and cache conditions when feasible.
- Isolate the first causal error, implement the narrowest authorized correction, and add a regression check when the cause is in repository behavior.
- Verify the repaired command or pipeline stage and state whether a remote retry remains necessary.
Boundaries
- Do not retry, cancel, rerun, edit secrets, or alter hosted CI settings without explicit authorization.
- Do not mistake a later cascade error for the root cause.
- Do not paste tokens, signed URLs, customer data, or full secret-bearing logs into output.
Completion Check
Report the failed stage, root cause evidence, change made or recommended, local verification, and any remaining remote validation.
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.
- 1mo ago First seen · 27 lines · 85 tokens per session scan A 05822ea41765
ci-debugger is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 331 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
Debug (reproduce -> isolate -> fix)
Systematically diagnose and fix a bug instead of guessing.
ci-self-heal
A diagnostic guide for analysing failed continuous-integration checks. Continuous integration, or CI, automatically tests and builds code changes; this guide classifies failures and suggests fixes without editing the code.
ci-triage
Parse CI failures, identify failing job/step, classify as flake, regression, env, or config. Use in CI sweeper loops before any fix attempt.
fix-failing-ci
Find out why a project's automated checks (CI) failed and fix the real cause: read the failing log, reproduce it on this machine, fix it without hiding the failure, and prove it passes.
ci-fix-monitor
Codex adapter for monitoring and fixing CI failures on opencode-swarm PRs. Use when diagnosing failed checks, fixing package-check (npm tarball) failures, resolving quality/lint/format errors, fixing macOS cross-platform file I/O failures, or watching a PR until all checks are green.
swarm-ci-monitor
Codex adapter for end-to-end CI monitoring of an already-reviewed PR in opencode-swarm. Use when the user wants the swarm to monitor a reviewed-and-approved PR's CI, research every failure exhaustively, fix end-to-end, iterate until green (max 5 cycles), then merge. Composes ci-fix-monitor for fix recipes.