Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add technicalpickles/pickled-claude-plugins/plugin install github-actionsWrote 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/skills/technicalpickles/pickled-claude-plugins/investigating-runs)<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/investigating-runs"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/investigating-runs.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01818 |
| Opus 5 | $0.00000 | $0.00909 |
| Sonnet 5 | $0.00000 | $0.00364 |
| Haiku 4.5 | $0.00000 | $0.00182 |
Grade A, and why
investigating-runs 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 8d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigating GitHub Actions Runs
Overview
This skill helps you investigate failing GitHub Actions runs. It covers checking status, finding the root failure, and reading log output efficiently — not authoring workflow YAML, not driving a fix-then-rerun loop. Load it when working with an existing run (failed CI, red PR check, "why is this broken").
Why gha-snapshot?
One command, one ref, gets you everything: run metadata, per-job status, the failed step's log tail, and annotations — in a single readable block. gh run view --log-failed is a firehose; gha-snapshot distills it.
Tool hierarchy
Use in this order. Don't skip ahead unless the current tier can't answer the question.
1. gha-snapshot (primary)
${CLAUDE_PLUGIN_ROOT}/scripts/gha-snapshot <ref>
Accepts any of:
| Input | Example |
|---|---|
| Full URL | gha-snapshot https://github.com/octocat/Hello-World/actions/runs/123 |
| Run ID (uses cwd's repo) | gha-snapshot 123 |
| PR number | gha-snapshot --pr 42 |
| Default (latest failed run on current branch) | gha-snapshot |
Flags: --tail N controls how many lines of failed-step log to include per failed job (default 50).
Exit 0 = snapshot rendered (even if the run failed). Exit 1 = couldn't resolve a run.
2. Raw gh CLI (secondary)
When the snapshot doesn't expose what you need:
gh run list --branch <branch> --status failure --limit 5
gh run view <run-id> --json jobs,conclusion,headSha,event
gh run view <run-id> --log # full log (huge)
gh run view <run-id> --log-failed # failed steps only
gh run rerun <run-id> --failed # transient infra only — see below
gh pr checks <pr-num>
gh workflow view <workflow>
See references/gh-cheatsheet.md for --json field names and jq patterns.
3. gh api (fallback)
For things the wrappers don't cover: GraphQL queries, raw check-run annotations, paged listings.
gh api repos/{owner}/{repo}/actions/runs/{run_id}/jobs
gh api repos/{owner}/{repo}/check-runs/{check_id}/annotations
What ships with it
3 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.
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.
- 8d ago First seen · 148 lines · 0 tokens per session scan A 0a0da64b5358
investigating-runs is a skill published in the GitHub repository technicalpickles/pickled-claude-plugins (10 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,818 tokens. 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.
Other skills, from other repositories
absolute-deflake
Flaky test fixes: detect nondeterministic tests empirically (repeat/shuffle/parallel runs), diagnose the root cause, fix it — never retry/skip/sleep — and verify across many randomized runs. Triggers on "absolute deflake", "fix flaky tests", "CI is flaky", "this test fails randomly/intermittently".
absolute-prune
Dead code and dependency cleanup, repo-wide: unused deps, unreferenced exports, unreachable code, orphaned files — removed only with tool evidence, in reversible waves. Runs on green main. For diff-scoped cleanup use absolute-simplify. Triggers on "absolute prune", "remove dead code", "find unused deps/exports", "what…
absolute-debt
Lint and typecheck debt paydown: clear pre-existing repo-wide lint/type violations and suppressions (@ts-ignore, # type: ignore) one rule per wave, fixing causes not symptoms. Runs on green main. For diff-scoped quality use absolute-simplify. Triggers on "absolute debt", "fix our lint warnings", "clear the type…
mk:fix
Diagnoses and fixes bugs, type errors, lint failures, CI/CD issues, and runtime errors via root-cause-first investigation. Use for defect remediation. NOT for investigation without a fix (see mk:investigate); NOT for build-only compilation errors (see mk:build-fix).
scientific-debugging
A method for debugging software by observing the problem, forming possible explanations, running small experiments, and then fixing and checking the result.
investigate-ci
Investigates GitHub Actions workflow failures for any repo. Fetches recent runs, identifies failures, extracts error logs, diagnoses root causes, and suggests fixes. Use when a deploy or CI workflow fails and you need to understand why.