drift: Skill for Claude Code

.github/skills/fix-failing-actions/SKILL.md

fix-failing-actions is a skill for Claude Code from mick-gsk/drift. It costs 78 tokens per session (2,693 once invoked), scanned A, original, MIT.

A troubleshooting guide for failed GitHub Actions, the automated checks that build, test, and release code. It is tailored to the drift repository and its Windows-based workflows.

In plain words
What is it for?
Use it to inspect action logs, find the failing workflow step, and fix problems in CI, release, security, documentation, Docker, or repository-hygiene jobs.
Why use it?
It helps identify why a check is red instead of guessing from a generic failure message. It covers common failures in tests, code checks, security checks, releases, documentation, Docker builds, and repository rules.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is mick-gsk/drift's own configuration. It tells Claude Code how to work on drift itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything drift configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/release_automation.py --full-release.

Part of the drift plugin — 31 skills, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to mick-gsk/drift. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mick-gsk/drift/main/.github/skills/fix-failing-actions/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mick-gsk/drift

Made for: Claude Code.

Or install drift, the plugin that ships this one along with the rest of its 31 skills, 17 agents.

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 fix-failing-actions

README.md
[![agentmods](https://agentmods.dev/badge/skills/mick-gsk/drift/fix-failing-actions/github.svg)](https://agentmods.dev/skills/mick-gsk/drift/fix-failing-actions)
Your own site
<a href="https://agentmods.dev/skills/mick-gsk/drift/fix-failing-actions"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/fix-failing-actions/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 fix-failing-actions

Your own site · 80×15
<a href="https://agentmods.dev/skills/mick-gsk/drift/fix-failing-actions"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/fix-failing-actions.svg" alt="Reviewed on agentmods" width="80" 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 2,693 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 $0.02693
Opus 5 $0.00039 $0.01347
Sonnet 5 $0.00016 $0.00539
Haiku 4.5 $0.00008 $0.00269

Measured 11d ago against content hash 68ca43ada805, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fix-failing-actions 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 11d 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.

.github/skills/fix-failing-actions/SKILL.md · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix Failing GitHub Actions

When to Use

  • A CI run on main or a PR is red
  • The release workflow failed
  • A security hygiene, repo-guard, or labeler job failed
  • You see a failed status check in a pull request
  • gh run list shows failed runs

Drift-Specific Context

All workflows in this repo run on Windows runners (windows-latest) with PowerShell. Python is resolved dynamically via $env:PYTHON_BIN (set by a resolver step). CI steps use make check equivalents split into: ruffmypypytestdrift analyze.

Key workflows and their failure modes:

Workflow File Common Failures
CI ci.yml pytest, mypy, ruff, check_version.py, check_model_consistency.py
Security Hygiene security-hygiene.yml detect-secrets, actionlint, zizmor, pip-audit
Release release.yml PSR version bump, PyPI publish, tag conflicts
Validate Release validate-release.yml SemVer format, CHANGELOG missing entry
Docs docs.yml mkdocs build error, broken links
Docker docker.yml build error, push credentials
Repo Guard repo-guard.yml check_repo_hygiene.py blocklist violation
Install Smoke install-smoke.yml pip install failure, CLI entry point missing
Doc Consistency doc-consistency.yml version mismatch in docs

Step 1: Identify the Failing Run

# List recent failed runs
gh run list --repo mick-gsk/drift --status failure --limit 10

# Or watch a specific run
gh run view <run-id> --repo mick-gsk/drift

If you have a URL like https://github.com/mick-gsk/drift/actions/runs/12345678, extract the run ID (12345678) and use it below.


Step 2: Fetch the Failure Logs

# Show only the failing steps
gh run view <run-id> --repo mick-gsk/drift --log-failed

# Or full log for a specific job
gh run view <run-id> --repo mick-gsk/drift --log

Parse the log output: Look for the first ##[error] or FAILED line — that is the root cause. Ignore everything after the first failure unless it looks like a separate independent failure.

Read the full file on GitHub · 304 lines

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. 11d ago First seen · 304 lines · 78 tokens per session scan A 68ca43ada805

Subscribe to this mod's changes

fix-failing-actions is a skill published in the GitHub repository mick-gsk/drift (15 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 2,693 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 2026-08-30.

Related

Other skills, from other repositories

atmos-lint

Atmos Terraform linting with TFLint: standalone atmos terraform lint, component-aware config discovery and toolchain versions, TFLint rule configuration, and lifecycle hooks/CI findings. Use when configuring, running, debugging, or documenting Terraform/OpenTofu linting in an Atmos project.

cloudposse/atmos · 64 tokens

roam

Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…

Cranot/roam-code · 86 tokens

truecourse-fix

Fix TrueCourse violations that have suggested fixes.

truecourse-ai/truecourse · 13 tokens

truecourse-list

List TrueCourse violations found in this repository.

truecourse-ai/truecourse · 12 tokens

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.

ZaxbyHub/opencode-swarm · 68 tokens

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.

ZaxbyHub/opencode-swarm · 75 tokens