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 sumithr/sumo-qa --skill sumo-qa-triaging-test-failuresgit clone --depth 1 https://github.com/sumithr/sumo-qaWrote 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/sumithr/sumo-qa/sumo-qa-triaging-test-failures)<a href="https://agentmods.dev/skills/sumithr/sumo-qa/sumo-qa-triaging-test-failures"><img src="https://agentmods.dev/badge/skills/sumithr/sumo-qa/sumo-qa-triaging-test-failures/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/sumithr/sumo-qa/sumo-qa-triaging-test-failures"><img src="https://agentmods.dev/badge/skills/sumithr/sumo-qa/sumo-qa-triaging-test-failures.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00121 | $0.03102 |
| Opus 5.5 | $0.00048 | $0.01241 |
| Sonnet 5.5 | $0.00024 | $0.00620 |
| Haiku 4.5 | $0.00012 | $0.00310 |
Grade A, and why
sumo-qa-triaging-test-failures 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 25d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triaging test failures
Separate why it failed from how to fix it: the same red bar can mean a product regression, a wrong test, stale fixture data, a broken environment, an order/timing race, or a flaky external service, each needing a different response. Patch before naming the cause and a test bug gets "fixed" in the product, or a real regression is buried under a rerun. The output is a cause classification plus the smallest next verification step, never a fix first.
Output discipline (mandatory)
Inherits the global discipline from using-sumo-qa: no internal taxonomy labels (say "the test's own expectation is stale", not "Cause: test_bug"), findings not framing, one question per turn.
The Iron Law
CLASSIFY, THEN ISOLATE — NEVER FIX FIRST. The first output for any failure is a named cause plus the single smallest next reproduction/isolation step, NOT a patch. Production code is touched ONLY after triage identifies a concrete product-behaviour gap. A test bug, fixture/data, environment/dependency, timing/order, or external-service flake is NOT a product gap and never licenses a production edit. A rerun is allowed only as a stated experiment testing one hypothesis — never "run it again and hope".
When to Use
sumo-qa-deciding-approach routes here on triage-test-failure: "this test keeps failing", "red in CI, green locally", "this test is flaky".
NOT for: a defect already pinned to a known product behaviour (regression-first via sumo-qa-implementing-with-tdd); a named uncovered gap ready to close (closed-loop-gap-fix via sumo-qa-closing-qa-gaps); strengthening weak-but-passing tests / killing mutation survivors (sumo-qa-strengthening-tests). Triage comes first and decides whether any apply.
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.
- 25d ago Changed · -2 lines f4e474e3e109
- 28d ago Changed · -6 tokens per session c7b33f501e17
- 1mo ago Changed · -1 lines 6fa78c0f5129
- 1mo ago First seen · 91 lines · 127 tokens per session scan A ebe1b20b4932
sumo-qa-triaging-test-failures is a skill published in the GitHub repository sumithr/sumo-qa (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 121 tokens to every session and 3,102 once invoked, about $0.0005 per session on Opus 5.5. 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
code-review
Reviews code for bugs, security issues, and best practices.
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…
extending-hobby-smoke-tests
Design, extend, review, or debug PostHog Hobby end-to-end smoke tests in bin/hobby-ci.py and .github/workflows/ci-hobby.yml. Use when adding an ingestion round trip, deciding whether a product belongs in Hobby CI, changing the CI Hobby service topology or API-key scopes, or diagnosing a smoke test that captures data…
agent-upkeep
Perform one small, scoped maintenance improvement to the Elements monorepo and open a single reviewable pull request. Use this skill for scheduled or unattended upkeep runs that improve unit test coverage for one file, fix one behavioral bug in one module, or move one off ESLint rule toward enforcement to reduce…
ring:test-driven-development
Enforcing the RED-GREEN-REFACTOR loop: write one failing test and watch it fail, write minimal code to pass, then refactor green. Use when starting implementation of a new feature or bugfix, or writing any new production code. Requires pasted failure output as proof of RED; code written before its test must be…