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.
npx skills add ShiplightAI/agent-skills --skill triagegit clone --depth 1 https://github.com/ShiplightAI/agent-skillsWrote 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.
[](https://agentmods.dev/skills/shiplightai/agent-skills/triage)<a href="https://agentmods.dev/skills/shiplightai/agent-skills/triage"><img src="https://agentmods.dev/badge/skills/shiplightai/agent-skills/triage/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.
<a href="https://agentmods.dev/skills/shiplightai/agent-skills/triage"><img src="https://agentmods.dev/badge/skills/shiplightai/agent-skills/triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
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 | $0.00033 | $0.00892 |
| Opus 5 | $0.00016 | $0.00446 |
| Sonnet 5 | $0.00007 | $0.00178 |
| Haiku 4.5 | $0.00003 | $0.00089 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage Failing Tests
Use this skill to reproduce, diagnose, and repair failing Shiplight YAML tests. If the application is broken or current behavior conflicts with the spec, report the mismatch instead of rewriting the test around it.
When To Use
Use /triage when:
- A Shiplight test run is failing
- A deployment or UI change broke existing tests
- Several tests may share the same failure source
- CI needs a best-effort repair/report pass
Skip /triage when:
- Creating new tests from scratch; use
/create-yaml-tests - Verifying UI code changes without failing tests; use
/verify - Tests pass and the task is only quality improvement
- The product is being intentionally redesigned and tests need planned rewriting
Required Context
Before editing YAML:
- Read the
create-yaml-testsreference guidesproject-layout.md,updating-tests.md,test-implementation-guide.md, andknowledge.md. - Read relevant
knowledge/notes for the failing area, environment, auth, data, and tooling. - Read the matching spec under
specs/tests/, if one exists. - Read
shiplight://yaml-test-specandshiplight://schemas/action-entity.
Ground Truth
When sources disagree, this precedence applies:
- Explicit user instruction
- Feature or journey spec in
specs/tests/ - Existing YAML test
goal, stepintent, andVERIFYassertions - Current app behavior
- Project context in
specs/context.mdandknowledge/ - Agent docs
- Agent inference
If current app behavior conflicts with a spec or test goal, report the mismatch. Do not silently rewrite intent to match current behavior.
Workflow
- Reproduce — run the specified target, or the narrowest relevant suite if no target was provided. If a failure looks transient, rerun the smallest affected target once before editing.
- Understand — read the failure output, relevant YAML, matching spec, related tests, and shared templates/functions/hooks before opening a browser or changing files.
- Inspect when needed — when logs and files are not enough, inspect the live app in a browser. Use the evidence needed for the failure: DOM, actions, locators, console logs, network logs, screenshots, or recordings.
- Fix minimally — change the smallest correct surface: YAML, template, helper function, auth setup, environment data, or spec. Do not touch passing tests unless they share the same broken source.
- Validate and rerun — validate edited YAML with
validate_yaml_test, then rerun the narrowest changed target. After batch fixes, rerun the original target once. - Reflect — update specs,
specs/context.md, orknowledge/when the session produced durable learning or corrected stale assumptions.
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 · 81 lines · 33 tokens per session scan A a40e727c5cde
triage is a skill published in the GitHub repository ShiplightAI/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 892 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.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.