ci-detective

ci-detective is a skill for Claude Code from mdelapenya/coding-skills. It costs 78 tokens per session (854 once invoked), scanned A, original, MIT.

A diagnostic guide for investigating failed checks in a pull request (PR), where proposed code changes are reviewed before merging. It compares failed tests with recent CI runs, meaning automated checks that build and test code.

In plain words
What is it for?
Use it to investigate failed GitHub Actions or GitLab CI jobs, check whether a test is flaky, and compare failures across recent runs.
Why use it?
It helps distinguish failures caused by the PR from tests that were already failing or behaving inconsistently. This gives you evidence before changing code or blaming the build system.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Part of the coding-skills plugin — 5 skills shipped together

Good fit Use it to investigate failed GitHub Actions or GitLab CI jobs, check whether a test is flaky, and compare failures across recent runs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mdelapenya/coding-skills/ci-detective
Install

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.

Any agent
npx skills add mdelapenya/coding-skills --skill ci-detective
Clone the repo
git clone --depth 1 https://github.com/mdelapenya/coding-skills

Made for: Claude Code.

Or install coding-skills, the plugin that ships this one along with the rest of its 5 skills.

Wrote 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.

agentmods badge for ci-detective

README.md
[![agentmods](https://agentmods.dev/badge/skills/mdelapenya/coding-skills/ci-detective.svg)](https://agentmods.dev/skills/mdelapenya/coding-skills/ci-detective)
Your own site
<a href="https://agentmods.dev/skills/mdelapenya/coding-skills/ci-detective"><img src="https://agentmods.dev/badge/skills/mdelapenya/coding-skills/ci-detective.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 854 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.00854
Opus 5 $0.00039 $0.00427
Sonnet 5 $0.00016 $0.00171
Haiku 4.5 $0.00008 $0.00085

Measured 7d ago against content hash e2427d73e458, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ci-detective 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 7d 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.

skills/ci-detective/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CI Detective

Investigate CI failures on a PR by cross-referencing failing tests against other recent runs to determine whether failures are pre-existing or introduced by the PR.

Do not assume failures are pre-existing or infrastructure-related. Always gather evidence first.

Supported CI Systems

This skill supports multiple CI platforms. Each platform has its own reference file under references/ with platform-specific commands and patterns.

Currently supported:

  • GitHub Actions — see references/github-actions.md
  • GitLab CI — see references/gitlab-ci.md

Planned:

  • Jenkins

When investigating, first detect which CI system the repository uses, then load the corresponding reference file for platform-specific commands.

Arguments

  • $1 — Number of recent runs to query (default: 10). Example: /ci-detective 20

Workflow

Step 1: Detect the CI system

Check the repository for CI configuration:

  • .github/workflows/ → GitHub Actions (load references/github-actions.md)
  • .gitlab-ci.yml → GitLab CI (load references/gitlab-ci.md)

If the CI system is not yet supported, inform the user and stop.

Step 2: Get failing job and test names from the current PR's run

Using the platform-specific commands from the loaded reference, identify the current branch's PR and its most recent failing workflow run. Record the workflow name, failing job names, and failing test names.

Step 3: Find recent completed runs of the same workflow on other branches

Query the last $1 runs (default: 10) and filter to completed runs on branches other than the current PR's branch. Select 3–5 from the results with a mix of conclusions (prefer at least one passing and one failing if available).

Step 4: Check if the same jobs/tests fail in those runs

For each selected run, check whether the same jobs failed. If a job failed in another run, fetch its logs to confirm the same test is failing.

Step 5: Classify each failure

Read the full file on GitHub · 85 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 7d ago First seen · 85 lines · 78 tokens per session scan A e2427d73e458

Subscribe to this mod's changes

ci-detective is a skill published in the GitHub repository mdelapenya/coding-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 854 once invoked, about $0.0004 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories