snosi: Command for GitHub Copilot

.github/prompts/triage-ci-failure.md

triage-ci-failure is a command for GitHub Copilot from frostyard/snosi. It costs 0 tokens per session (297 once invoked), scanned A, original, MIT.

A reusable prompt for investigating a failed CI workflow, where CI means automated checks that run during development. It tells the agent to find the first real error, trace it to the responsible script, reproduce it locally, and report the fix.

In plain words
What is it for?
Use it to diagnose failing workflow runs, inspect job logs, reproduce the smallest failing case, fix the root cause, and document the result.
Why use it?
It helps distinguish the original failure from later cascade errors and discourages weakening tests just to make a workflow pass.

Command for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt.

This is frostyard/snosi's own configuration. It tells GitHub Copilot how to work on snosi 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 snosi configures →

Reuse

Borrowing it

Nothing to install: this file belongs to frostyard/snosi. 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/frostyard/snosi/main/.github/prompts/triage-ci-failure.md
Clone the repo
git clone --depth 1 https://github.com/frostyard/snosi

Made for: GitHub Copilot.

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 triage-ci-failure

README.md
[![agentmods](https://agentmods.dev/badge/commands/frostyard/snosi/triage-ci-failure/github.svg)](https://agentmods.dev/commands/frostyard/snosi/triage-ci-failure)
Your own site
<a href="https://agentmods.dev/commands/frostyard/snosi/triage-ci-failure"><img src="https://agentmods.dev/badge/commands/frostyard/snosi/triage-ci-failure/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 triage-ci-failure

Your own site · 80×15
<a href="https://agentmods.dev/commands/frostyard/snosi/triage-ci-failure"><img src="https://agentmods.dev/badge/commands/frostyard/snosi/triage-ci-failure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 297 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 $0.00000 $0.00297
Opus 5 $0.00000 $0.00148
Sonnet 5 $0.00000 $0.00059
Haiku 4.5 $0.00000 $0.00030

Measured 4d ago against content hash a57320322d94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

triage-ci-failure 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 4d 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/prompts/triage-ci-failure.md · 25 lines

What it actually says

Prompt: triage a CI failure

Goal: find the root cause of the failure in <workflow / run URL>.

Steps:

  1. List recent runs of the workflow and identify the failing run and job.
  2. Fetch the failing job's logs and quote the first genuine error, not the final summary line — later failures in this repository's workflows are usually cascades of an earlier one.
  3. Map the job back to the script it calls. The workflows are thin callers: validate.yml runs shellcheck, check-runtime-etc-guard.sh, check-native-publication-guard.sh, and the fixture tests in test/; build-native-images.yml calls shared/native-ab/publish/*.sh and shared/native-ab/ci/*.sh; build-images.yml calls shared/outformat/image/buildah-package.sh.
  4. Reproduce locally with the smallest command that exercises the same code path — usually a single script from test/ — before changing anything.
  5. Fix the root cause in the script or configuration. Do not weaken, skip, or delete an assertion to make a job green; if an assertion is genuinely wrong, say so explicitly and explain why in the pull request.

Report back with: the failing job, the first real error, the root cause, the fix, and the command that now passes locally.

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. 4d ago First seen · 25 lines · 0 tokens per session scan A a57320322d94

Subscribe to this mod's changes

triage-ci-failure is a command published in the GitHub repository frostyard/snosi (24 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 297 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 2026-09-06.