fix-ci

A command for investigating a failed continuous integration (CI) run, where automated checks test code changes before they are merged.

In plain words
What is it for?
Use it to find failing jobs, inspect logs, reproduce problems locally, and propose a fix.
Why use it?
It helps identify the first real error in a failed run and separate it from later errors caused by that failure.

Command for Claude Code

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.

agentmods
npx agentmods add commands/oolab-labs/patchwork-os/fix-ci
Clone the repo
git clone --depth 1 https://github.com/Oolab-labs/patchwork-os

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 506 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00010 $0.00506
Opus 5 $0.00005 $0.00253
Sonnet 5 $0.00002 $0.00101
Haiku 4.5 $0.00001 $0.00051

Measured 2d ago against content hash 9d1e80ba6e98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fix-ci 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 2d 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.

.claude/commands/fix-ci.md · 49 lines

What it actually says

Fix Failing CI

Diagnose the failing CI run $1 (a workflow run id, or a PR number whose checks are red — if omitted, use the most recent failing run on the current branch).

Step 1: Locate the Failing Run

If $1 is a PR number, call githubViewPR to find its check runs. Otherwise call githubListRuns and pick the most recent failure on the current branch. Report the run id and which job(s) failed.

Step 2: Pull the Logs

Call githubGetRunLogs for the failing run. Identify the failing step and the first real error — not downstream noise. Common failure shapes in this repo:

  • typechecktsc -p tsconfig.tests.core.json is stricter than vitest (noUnusedLocals); import-path errors slip past local vitest runs.
  • biome — run getDiagnostics to reproduce; never npx biome blindly.
  • vitest — coverage gates are 75% lines / 70% branches / 75% functions.
  • property tests — may pass locally and fail in CI on a different seed; pin the failing seed from the CI output.
  • Windows CIstat.mode asserts fail on NTFS; platform-guard them.

Step 3: Reproduce Locally

Reproduce the failure with the equivalent bridge tool — runTests, getDiagnostics (replaces tsc/eslint/biome) — NOT raw shell. Confirm you see the same error before proposing anything.

Step 4: Propose the Fix

If the failure is a genuine bug, follow the Bug Fix Protocol: write a failing test first, then fix. If it is a flake (seed-dependent property test, etc.), pin the seed or tighten the generator. Present the diff to the user for approval before committing.

Step 5: Report to User

Show: the failing job, the root-cause error, whether it reproduced locally, and the proposed fix (or the failing test, if a fix needs approval first).

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. 2d ago First seen · 49 lines · 10 tokens per session scan A 9d1e80ba6e98

Subscribe to this mod's changes

fix-ci is a command published in the GitHub repository Oolab-labs/patchwork-os (30 stars, last pushed 2d ago), licensed MIT. It adds 10 tokens to every session and 506 once invoked, about $0.0001 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 2026-08-30.