ci-triage

ci-triage is a skill for Codex from coo1white/cool-workflow. It costs 66 tokens per session (348 once invoked), scanned A, original, BSD-2-Clause.

A troubleshooting guide for failed continuous-integration checks, builds, tests, releases, and smoke tests. Continuous integration, or CI, automatically checks code changes before they are accepted.

In plain words
What is it for?
Use it to diagnose GitHub Actions failures, local npm test or build errors, release gates, smoke tests, and generated-manifest checks, then verify the proposed fix.
Why use it?
It focuses the investigation on the first useful error in the logs and separates confirmed evidence from guesses, reducing unnecessary edits.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md; mentions Codex.

Part of the cool-workflow plugin — 5 skills, 2 commands, 1 agent, 1 MCP server shipped together

Good fit Use it to diagnose GitHub Actions failures, local npm test or build…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/coo1white/cool-workflow/ci-triage
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 coo1white/cool-workflow --skill ci-triage
Clone the repo
git clone --depth 1 https://github.com/coo1white/cool-workflow

Made for: Codex.

Or install cool-workflow, the plugin that ships this one along with the rest of its 5 skills, 2 commands, 1 agent, 1 MCP server.

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 ci-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/coo1white/cool-workflow/ci-triage.svg)](https://agentmods.dev/skills/coo1white/cool-workflow/ci-triage)
Your own site
<a href="https://agentmods.dev/skills/coo1white/cool-workflow/ci-triage"><img src="https://agentmods.dev/badge/skills/coo1white/cool-workflow/ci-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 348 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 $0.00066 $0.00348
Opus 5 $0.00033 $0.00174
Sonnet 5 $0.00013 $0.00070
Haiku 4.5 $0.00007 $0.00035

Measured 6d ago against content hash b575b6d5aca9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ci-triage 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 6d 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.

plugins/cool-workflow/skills/ci-triage/SKILL.md · 51 lines

What it actually says

CI Triage

Overview

Triage the failure before editing. Keep stdout/log evidence separate from diagnosis, identify the first failing command, and end with one verifier command that proves the proposed fix.

Workflow

  1. Capture the failing command, exit code, and the earliest meaningful error.
  2. Classify the failure as code, test expectation, generated artifact drift, environment, timeout, or external service.
  3. Inspect only the files needed to explain that first failure.
  4. Propose or implement the smallest fix.
  5. Run the narrow verifier first, then the full gate when the fix is plausible.
  6. Write the lesson back to AGENTS.md's Build Memory section, an eval case, or the matching workflow skill when the failure pattern is likely to recur.

Commands

npm run build
npm test
npm run gen:manifests -- --check
npm run index:check
git diff --check

Use smoke tests directly for narrow verification:

node test/<name>-smoke.js

Output Rules

  • Lead with the failing command and root cause.
  • Quote only the shortest relevant log lines.
  • Separate "confirmed" from "inference".
  • Include the verifier commands actually run or still required.
Files

What ships with it

1 file 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.

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. 6d ago First seen · 51 lines · 66 tokens per session scan A b575b6d5aca9

Subscribe to this mod's changes

ci-triage is a skill published in the GitHub repository coo1white/cool-workflow (2 stars, last pushed today), licensed BSD-2-Clause. It adds 66 tokens to every session and 348 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.