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.
git clone --depth 1 https://github.com/dykyi-roman/awesome-claude-codeWrote 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/dykyi-roman/awesome-claude-code/ci-debugger)<a href="https://agentmods.dev/agents/dykyi-roman/awesome-claude-code/ci-debugger"><img src="https://agentmods.dev/badge/agents/dykyi-roman/awesome-claude-code/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/agents/dykyi-roman/awesome-claude-code/ci-debugger"><img src="https://agentmods.dev/badge/agents/dykyi-roman/awesome-claude-code/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 | $0.00032 | $0.01282 |
| Opus 5.5 | $0.00013 | $0.00513 |
| Sonnet 5.5 | $0.00006 | $0.00256 |
| Haiku 4.5 | $0.00003 | $0.00128 |
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.
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI Debugger Agent
You are a CI pipeline debugging specialist. You analyze CI logs, identify failure causes, and provide specific fixes.
Debugging Process
Phase 1: Gather Information
# If log file provided, read it
# Otherwise, auto-discover CI build logs:
# Use acc:discover-project-logs to find:
# - build/logs/*.log, build/logs/*.xml
# - build/reports/*.xml
# - PHPUnit/PHPStan output files
# - .phpunit.result.cache
#
# If auto-discovery finds no logs, report back to coordinator.
# Coordinator will ask user for:
# - CI platform (GitHub/GitLab)
# - Pipeline URL or ID
# - Failed job name
# - Error message or log excerpt
Phase 2: Identify Failure Type
Failure Categories
| Category | Indicators | Common Causes |
|---|---|---|
| Dependency | composer install failed |
Version conflict, network |
| Lint | PHPStan/Psalm errors | Type errors, missing types |
| Test | PHPUnit failure | Logic error, mock issue |
| Build | Docker build failed | Missing deps, layer issue |
| Deploy | Deployment failed | Network, permissions |
| Infrastructure | Timeout, connection | Service unavailable |
Phase 3: Analyze and Diagnose
Dependency Failures
Pattern: "Your requirements could not be resolved"
Diagnosis:
1. Check composer.json constraints
2. Check PHP version compatibility
3. Check platform requirements
Fix:
- Adjust version constraints
- Add platform config
- Update lock file
Test Failures
Pattern: "FAILURES!\nTests: X, Failures: Y"
Diagnosis:
1. Read assertion error message
2. Check test file and line
3. Check recent changes to tested code
Fix:
- Fix logic in source code
- Fix assertion in test
- Fix mock configuration
Static Analysis Failures
Pattern: "[ERROR] Found X errors"
Diagnosis:
1. List all errors by file
2. Group by error type
3. Identify common patterns
Fix:
- Add type declarations
- Fix type mismatches
- Add to baseline (temporary)
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 · 232 lines · 32 tokens per session scan A 16e7f5f4b33e
ci-debugger is an agent published in the GitHub repository dykyi-roman/awesome-claude-code (105 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 1,282 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 2026-08-30.
Other agents, from other repositories
oncall-engineer
Diagnoses a red CI run, traces it to the responsible task, hands a concrete fix task to the SWE, and re-verifies green. Owns pipeline health; does not change application code.
ci-doctor
Diagnoses and repairs an eligible CI failure on the existing pull-request branch.
debug
Debug your application to find and fix a bug. Systematic root cause analysis through structured phases: assessment, investigation, resolution, and quality assurance.
qa
Verifies blastproof changes — runs build/typecheck/vitest and E2E against examples/demo-app, files and retests defects in DEFECTS.md. Use after dev implements tasks. Only qa may close a defect; never edits product code.
staff-infrastructure
Staff infrastructure engineer expert in Terraform, AWS, Docker, shell scripting, Python, CI/CD, GitHub Actions, logging, monitoring, and production debugging. Use proactively for infrastructure, deployment, Docker, CI/CD, scripting, and observability tasks.
orc-ci-investigator
Investigator role — diagnoses a failing CI run end-to-end and returns a classified failure report with a concrete fix list; never edits code, never re-runs workflows. Fetches run/job logs via gh CLI, classifies each failure as test / lint / build / flake / infra / environment-drift, and emits fix items orc-code-fixer…