source-command-fix-ci

source-command-fix-ci is a skill for Claude Code from juan294/cc-rpi. It costs 14 tokens per session (499 once invoked), scanned A, original, MIT.

An automated workflow for diagnosing the latest GitHub Actions CI run and fixing its reported failures. CI, or continuous integration, automatically checks code changes with tests and other checks.

In plain words
What is it for?
Use it when a branch's latest CI run fails because of tests, type checking, linting, or a build. It groups failures, investigates their causes, and verifies the fixes.
Why use it?
It removes the need to inspect failure logs and track each failing check manually. It fixes source code rather than weakening or deleting tests, then runs the full test suite locally.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

Part of the cc-rpi plugin — 36 skills, 19 commands, 2 hooks shipped together

Good fit Use it when a branch's latest CI run fails because of tests, type checking, linting, or a build. It groups failures, investigates their causes, and verifies the fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/juan294/cc-rpi/source-command-fix-ci
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 juan294/cc-rpi --skill source-command-fix-ci
Clone the repo
git clone --depth 1 https://github.com/juan294/cc-rpi

Made for: Claude Code.

Or install cc-rpi, the plugin that ships this one along with the rest of its 36 skills, 19 commands, 2 hooks.

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 source-command-fix-ci

README.md
[![agentmods](https://agentmods.dev/badge/skills/juan294/cc-rpi/source-command-fix-ci/github.svg)](https://agentmods.dev/skills/juan294/cc-rpi/source-command-fix-ci)
Your own site
<a href="https://agentmods.dev/skills/juan294/cc-rpi/source-command-fix-ci"><img src="https://agentmods.dev/badge/skills/juan294/cc-rpi/source-command-fix-ci/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.

agentmods 80×15 button for source-command-fix-ci

Your own site · 80×15
<a href="https://agentmods.dev/skills/juan294/cc-rpi/source-command-fix-ci"><img src="https://agentmods.dev/badge/skills/juan294/cc-rpi/source-command-fix-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 499 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 $0.00014 $0.00499
Opus 5 $0.00007 $0.00249
Sonnet 5 $0.00003 $0.00100
Haiku 4.5 $0.00001 $0.00050

Measured 5d ago against content hash d03b378e3601, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

source-command-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 5d 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.

.agents/skills/source-command-fix-ci/SKILL.md · 56 lines

What it actually says

source-command-fix-ci

Use this skill when the user asks to run the migrated source command fix-ci.

Command Template

Self-healing CI: diagnose and fix all failing tests autonomously.

Model tier: sonnet — Sonnet 5 (1M context) session. All subagents: model: "sonnet".

Process:

  1. Get the latest CI run for the current branch: gh run list --branch $(git branch --show-current) --limit 1 --json databaseId,conclusion,status If CI is green or still running, report status and stop.

  2. Get the failure logs: gh run view <run-id> --log-failed 2>&1 | tail -200

  3. Parse failures into individual test/check failures. Group by:

    • Type errors (typecheck)
    • Lint errors
    • Test failures (list each failing test)
    • Build failures
  4. For each failing test, spawn a sub-agent (model: "sonnet") to: a. Read the failing test file and the source file it covers b. Identify the root cause from the error message c. Fix the SOURCE code (never weaken or delete a test) d. Verify that specific test passes locally

  5. For typecheck/lint/build failures, fix them directly (these are usually straightforward).

  6. After all fixes, run the full test suite locally: pnpm run typecheck 2>&1; pnpm run lint 2>&1; pnpm run test 2>&1

  7. If new failures appear, repeat the fix cycle (max 3 iterations).

  8. When all checks pass, commit with message: fix: resolve CI failures [auto] Then push and spawn a background agent to verify CI passes.

Rules:

  • Never weaken a test to make it pass — fix the source code.
  • Never delete a test.
  • If a failure is flaky (passes locally, fails in CI), note it but don't skip.
  • If stuck after 3 fix cycles, stop and report what remains broken.
  • Verify the current branch before committing.
  • Normal CI repair happens on the branch under test. Never push directly to main without explicit approval.
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. 5d ago First seen · 56 lines · 14 tokens per session scan A d03b378e3601

Subscribe to this mod's changes

source-command-fix-ci is a skill published in the GitHub repository juan294/cc-rpi (5 stars, last pushed 5d ago), licensed MIT. It adds 14 tokens to every session and 499 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 2026-09-06.