ci-debug-loop

A workflow for watching a GitHub Actions continuous-integration run, diagnosing failures from its logs, and applying fixes. Continuous integration automatically builds and tests code when changes are pushed.

In plain words
What is it for?
Use it to find and watch a run, inspect failed jobs, identify the first failure, fix the code, push the change, and repeat the checks.
Why use it?
It turns a failing build or test run into an iterative process that can continue until the checks pass or the issue needs escalation.

Skill for Claude CodeCodex

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 skills/paultyng/skill-issue/ci-debug-loop
Any agent
npx skills add paultyng/skill-issue --skill ci-debug-loop
Clone the repo
git clone --depth 1 https://github.com/paultyng/skill-issue

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 908 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 $0.00062 $0.00908
Opus 5 $0.00031 $0.00454
Sonnet 5 $0.00012 $0.00182
Haiku 4.5 $0.00006 $0.00091

Measured 2d ago against content hash 1bc9af92fb61, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ci-debug-loop 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.

skills/ci-debug-loop/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CI Debug Loop

Iteratively watch CI, diagnose failures, fix, and re-trigger until the run passes or escalation is needed.

1. Identify the Run

Find the latest run for the current branch:

gh run list --branch $(git branch --show-current) --limit 1 --json databaseId,status,conclusion,name

If a specific run ID or workflow is provided by the user, use that instead.

2. Watch

If the run is still in progress:

gh run watch <run_id> --exit-status

If it already completed, proceed to diagnosis.

3. Diagnose Failure

On failure, fetch logs for the failed job(s):

gh run view <run_id> --log-failed

Delegate log analysis to a two-stage subagent pipeline when the failed-log output is more than ~200 lines. CI logs flood main context fast and the parent only needs the root cause, not the raw output. Per parallelize-subagents, delegate-investigation, and subagent-model-routing:

Stage 1 — Extract (Haiku): Spawn an Explore subagent (model: haiku) per failed job (parallel if multiple jobs failed). Prompt: paste the command to fetch the log (not the log itself); ask for "first failing assertion + ~10 lines of surrounding context, ≤50 lines, prefixed with Status: ...". Haiku handles the mechanical extraction; no interpretation needed at this stage.

Stage 2 — Interpret (Sonnet): After Stage 1 completes, spawn a generalPurpose subagent (model: sonnet) with the Stage 1 structured output pasted inline plus the failure categories below. Ask for "likely root cause + file:line if identifiable, ≤100 words, prefixed with Status: ...".

  • Parent receives the Stage 2 summary, decides the fix.

For short logs (<200 lines), inspect inline.

Common failure categories:

  • Build errors: compilation failures, missing dependencies
  • Test failures: assertion errors, timeouts, flaky tests
  • Auth/permissions: token scopes, registry auth, SSH keys
  • Config/YAML: syntax errors, wrong flags, missing env vars, heredoc issues
  • Infrastructure: runner issues, Docker rate limits, service unavailability

Read the full file on GitHub · 90 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. 2d ago First seen · 90 lines · 62 tokens per session scan A 1bc9af92fb61

Subscribe to this mod's changes

ci-debug-loop is a skill published in the GitHub repository paultyng/skill-issue (9 stars, last pushed 21d ago), licensed MIT. It adds 62 tokens to every session and 908 once invoked, about $0.0003 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.