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-strengthening-testsgit 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-strengthening-tests)<a href="https://agentmods.dev/skills/sumithr/sumo-qa/sumo-qa-strengthening-tests"><img src="https://agentmods.dev/badge/skills/sumithr/sumo-qa/sumo-qa-strengthening-tests/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-strengthening-tests"><img src="https://agentmods.dev/badge/skills/sumithr/sumo-qa/sumo-qa-strengthening-tests.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 | $0.00069 | $0.02745 |
| Opus 5 | $0.00034 | $0.01373 |
| Sonnet 5 | $0.00014 | $0.00549 |
| Haiku 4.5 | $0.00007 | $0.00275 |
Grade A, and why
sumo-qa-strengthening-tests 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 9d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strengthening tests
Help the user kill weak assertions and surviving mutants by walking each survivor one at a time: triage tautology vs real, pick a technique, draft the strengthening test, confirm. The user has judgement context (is this mutant "real" given how the code is consumed in practice?) the AI can't infer from the report alone — surface it through questions, don't assume it.
Announce at start: "Killing the mutation survivors, one at a time."
Output discipline (mandatory)
Inherits the global discipline from using-sumo-qa: output discipline (never surface internal taxonomy labels — say "behaviour change in pricing", not "Classification: business_logic_change"), output economy (spend output on findings not framing; no preamble or self-narration; one question per turn; no closing pleasantries), knowledge authority hierarchy, internal scaffolding stays internal, and specialty-tool fit.
The Iron Law
PRODUCTION CODE STAYS UNCHANGED. Only test code moves; equivalent mutants get suppressed in tool config, not "killed" by tautological tests that re-state the production code.
When to Use
sumo-qa-deciding-approach routes here for strengthen-test-coverage. User intents:
- "raise coverage on module X"
- "Pitest shows N surviving mutants — kill them"
- "Stryker / mutmut surfaced weak assertions"
- "strengthen the tests on the order calculator"
Production code is locked. The job is to make the EXISTING tests stronger.
Checklist
You MUST work through these in order. Steps 1–3 are AI-only homework (no user questions). The user's confirmation gates steps 4 onward, and steps 5–7 repeat per target (each surviving mutant, or — when no report exists — each weak assertion the user named, which skips straight to step 7).
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.
- 9d ago First seen · 112 lines · 69 tokens per session scan A d5e53513f572
sumo-qa-strengthening-tests is a skill published in the GitHub repository sumithr/sumo-qa (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 2,745 once invoked, about $0.0003 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
live-audit
Audit steam-games-mcp — build/test/lint gate, live MCP tool edge-case sweep (input validation, SteamID64/vanity/appid edge cases, key-gating), and source-level code review. Use when asked to test/audit the published or just-fixed steam-games-mcp package, hunt for bugs/edge cases, or repeat "the same kind of testing as…
pr-quality-cycle
Combined PR quality workflow: address inline review comments AND fix Codecov patch coverage gaps in one end-to-end cycle. Use when a PR has both review feedback and coverage regression, or when you want a single checklist that covers triage, code fixes, test additions, verification, and push-gate validation before…
qa
QA test a live website with Axon discovery/content evidence plus browser automation when interaction is required. Use when the user wants exploratory QA, form testing, navigation/link checks, responsive checks, performance observations, bug reports, or a pre-launch quality review.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
harness-engineering-lifecycle
Design, implement, and integrate generalized validation harnesses across a producer-consumer boundary after a local harness contract exists. Use when refactoring custom validation CLIs/MCPs for large polyrepos, extending Steward across sibling repos, or deploying a local tool to a consumer project for dogfooding and…