What is detect-permafail?

A failure-pattern checker for continuous integration jobs, which are automated builds and tests. It compares 2–10 consecutive failures to decide whether the same permanent problem keeps recurring or the failures are flaky and inconsistent.

Use it to examine consecutive OpenShift CI Prow job failures and classify them as permafailing or flaky using their job artifacts.

It helps distinguish a real, repeatable failure from an intermittent one, so repeated test failures are not misdiagnosed as random glitches.

detect-permafail — Skill for Claude Code by openshift-eng

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 openshift-eng/ai-helpers --skill detect-permafail

Clone the repo

git clone --depth 1 https://github.com/openshift-eng/ai-helpers

Made for: Claude Code.

Or install ci, the plugin that ships this one along with the rest of its 34 skills, 21 commands, 2 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/detect-permafail.svg)](https://agentmods.dev/skills/openshift-eng/ai-helpers/detect-permafail)

Your own site

<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/detect-permafail"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/detect-permafail.svg" alt="Measured on agentmods" height="20"></a>

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 10,296 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00022	$0.10296
Opus 5	$0.00011	$0.05148
Sonnet 5	$0.00004	$0.02059
Haiku 4.5	$0.00002	$0.01030

Measured 8d ago against content hash eea95463ef38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

detect-permafail 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.

plugins/ci/skills/detect-permafail/SKILL.md · 885 lines

How it starts

The opening of the file, as written. The whole thing — 885 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Detect Permafail

When to Use This Skill

Use this skill when you have 2-10 consecutive failures of the same job and need to determine if the failures represent a systematic/permanent failure (permafail) versus a flaky failure. This is critical for CI/CD pipeline analysis to distinguish between:

Permafail: A systematic failure affecting the same test(s) or infrastructure issue, detected by analyzing comparable runs (same failure type):
- 2-3 comparable runs: All must have the same failure (100% match)
- 4-5 comparable runs: At least 4 must have the same failure (80% match)
- 6-10 comparable runs: At least ceil(count × 0.7) must have the same failure (70% match)
Flaky: Non-deterministic failures with varying root causes, or failures that don't meet the permafail thresholds

Prerequisites

Access to OpenShift CI Prow job artifacts via gcsweb URLs
Access to the Bash tool for running plugins/ci/scripts/classify-job-failures.py
Python with the requests package available for artifact fetching
Knowledge of Prow artifact structure (from fetch-prowjob-json and prow-job-artifact-search skills)
2-10 URLs pointing to consecutive job failures (from Prow/OpenShift CI, ordered newest to oldest)
Job name context to verify consistency across all failures
PR information to provide context for analysis

Implementation Steps

Step 1: Validate Inputs

Standard Mode (URL-based):

Verify that all required inputs are present with expected types and constraints:

failure_urls: Array of 2-10 strings matching Prow job URL pattern https://prow.ci.openshift.org/view/gs/<bucket>/<path>/<job-name>/<build-id> where path may be logs/, pr-logs/pull/, or other GCS paths (must be consecutive runs, ordered newest to oldest)
job_name: Non-empty string identifier of the job being analyzed
pr_info: Object containing PR number (integer) and repository context (string)
Each URL must match the Prow job URL pattern above

Reject requests if:

URLs count is less than 2 or more than 10
Job names don't match across all URLs (validate via prowjob.json metadata, not path position)
PR context is missing

Read the full file on GitHub · 885 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.

8d ago First seen · 885 lines · 22 tokens per session scan A eea95463ef38

Subscribe to this mod's changes

detect-permafail is a skill published in the GitHub repository openshift-eng/ai-helpers (116 stars, last pushed 3d ago), licensed Apache-2.0. It adds 22 tokens to every session and 10,296 once invoked, about $0.0001 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.

CI and CD Debugging DevOps and cloud

smoke-test

Health smoke tests + auto-fix for gbrain installs (and OpenClaw services when present). Run after machine/container restarts or whenever something seems broken. Tests critical services, auto-fixes bounded local issues, and reports worker topology without starting daemons. Extensible via user-defined test scripts in…

garrytan/gbrain · 79 tokens

mcore-create-issue

Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.

NVIDIA/skills · 26 tokens

debug-task

Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time when it should be cached, or when outputs are empty or missing after a…

moonrepo/moon · 231 tokens

detect-permafail