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-suggesting-external-skillgit 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-suggesting-external-skill)<a href="https://agentmods.dev/skills/sumithr/sumo-qa/sumo-qa-suggesting-external-skill"><img src="https://agentmods.dev/badge/skills/sumithr/sumo-qa/sumo-qa-suggesting-external-skill/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-suggesting-external-skill"><img src="https://agentmods.dev/badge/skills/sumithr/sumo-qa/sumo-qa-suggesting-external-skill.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 | $0.00120 | $0.02672 |
| Opus 5 | $0.00060 | $0.01336 |
| Sonnet 5 | $0.00024 | $0.00534 |
| Haiku 4.5 | $0.00012 | $0.00267 |
Grade A, and why
sumo-qa-suggesting-external-skill 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 10d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suggesting an external skill
Announce at start: "Checking external skills through sumo-qa — no native sumo-qa capability fits."
Output discipline (mandatory)
Inherits the global discipline from using-sumo-qa: output discipline (never surface internal taxonomy labels — including entry_kind — say "this needs a PDF-to-markdown converter first", not "entry_kind: conversion"), 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
The sumo-qa MCP server owns external-skill lifecycle. Search, install, local lookup, and execution handoff go through sumo_qa_search_external_skills, sumo_qa_install_external_skill, sumo_qa_check_external_skill_installed, and sumo_qa_execute_external_skill. Install is always gated on the user's explicit y. Never run sudo from this flow.
When to Use
Entered two ways, never cold; the mode is carried by entry_kind:
entry_kind: qa—sumo-qa-deciding-approachfound no native approach fits and the intent needs a tool/framework/QA surface sumo-qa doesn't natively cover (Playwright/Cypress E2E, accessibility audits, k6/Locust load, Pact contract tests, type checking, flaky-test quarantine).entry_kind: conversion— an ingestion source (PDF/PPTX/URL/docx reportedunsupported_source) needs converting to markdown first. The gap is a converter, not a test tool.
Any install is gated by the per-candidate [y/N] prompt below; no global switch.
Checklist
You MUST work through these steps in order. External lifecycle operations are MCP tool calls, not host-shell npx calls.
- Check local install first. Call
sumo_qa_check_external_skill_installedif the router or user named a likely skill. If found, callsumo_qa_execute_external_skillwith the original intent and follow the returnedskill_body. If that execute returns anisError, do NOT stop — fall through to step 2 and search for an alternative.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 85 lines · 120 tokens per session scan A 863b11c3162e
sumo-qa-suggesting-external-skill is a skill published in the GitHub repository sumithr/sumo-qa (6 stars, last pushed today), licensed Apache-2.0. It adds 120 tokens to every session and 2,672 once invoked, about $0.0006 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…