triage

A guide for investigating the newest failed continuous-integration (CI) run for a software component. It checks failed jobs and steps, reads available logs and workflow settings, then labels the likely cause.

In plain words
What is it for?
Use it to diagnose whether a failed build or test comes from configuration, code, security checks, or infrastructure problems.
Why use it?
It gathers the failure details in one investigation instead of making you search through runs, jobs, logs, and configuration manually.

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/cloudbees-oss/devops-agent-kit/triage
Any agent
npx skills add cloudbees-oss/devops-agent-kit --skill triage
Clone the repo
git clone --depth 1 https://github.com/cloudbees-oss/devops-agent-kit

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 522 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 $0.00033 $0.00522
Opus 5 $0.00016 $0.00261
Sonnet 5 $0.00007 $0.00104
Haiku 4.5 $0.00003 $0.00052

Measured yesterday against content hash b06fbd15c02b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

.claude/skills/triage/SKILL.md · 51 lines

What it actually says

Triage Failed Run: $ARGUMENTS

  1. Search for the component using components_search

  2. Pull recent runs using runs_list(limit=10)

  3. Filter for FAILED runs. Skip any with workflow names containing "code_scan"

  4. For the latest failed run: a. automation_jobs_list — list all jobs and their statuses b. For each failed job, identify the failing step c. logs_list — attempt to pull logs from the failing step NOTE: If this returns a 500 error, proceed without logs. Analyze based on step names, statuses, and durations instead. d. workflow_get_content — read the workflow YAML to understand what each step does and identify configuration issues

  5. Classify the failure:

    • CONFIG: Workflow/pipeline configuration error (missing inputs, invalid action references, YAML syntax). Look for validation errors.
    • CODE: Compilation failure or test failure caused by a code change. Check if earlier steps (build, compile) passed.
    • SECURITY: Security scan gate failure (Gitleaks, SAST, SCA). Cross-reference with security_findings_summary_get.
    • ENVIRONMENT: Infrastructure issue — timeouts, connection refused, resource exhaustion, runner unavailability.
    • KNOWN: Matches a pattern from previous triage (same step, same error).
  6. Enrich with security context: a. security_findings_summary_get — check if the component has open security findings that may be related to the failure

  7. Present a structured triage report:

    • Run ID, workflow name, trigger, timestamp
    • Step-by-step results table (step name, status, duration)
    • Root cause analysis with specific evidence
    • Classification (CONFIG/CODE/SECURITY/ENVIRONMENT/KNOWN)
    • Fix recommendation
  8. Offer next actions:

    • File a Jira ticket for the issue (/file-ticket)
    • Post the summary to Slack
    • Comment on the relevant GitHub PR
    • If the fix is a workflow config change, offer to apply it via workflow_update_content (with user confirmation)
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. yesterday First seen · 51 lines · 33 tokens per session scan A b06fbd15c02b

Subscribe to this mod's changes

triage is a skill published in the GitHub repository cloudbees-oss/devops-agent-kit (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 522 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens