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 agentmods add skills/sumithr/sumo-qa/using-sumo-qanpx skills add sumithr/sumo-qa --skill using-sumo-qagit clone --depth 1 https://github.com/sumithr/sumo-qaWhat 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 | $0.00127 | $0.03701 |
| Opus 5 | $0.00063 | $0.01851 |
| Sonnet 5 | $0.00025 | $0.00740 |
| Haiku 4.5 | $0.00013 | $0.00370 |
Grade A, and why
using-sumo-qa 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 3d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using sumo-qa
Announce at start: "Routing this QA intent."
Output discipline (mandatory)
Never surface internal taxonomy labels in user-facing output. No "Classification: X", "Approach: Y", "Per the checklist", "Step 3 of 6". The taxonomy is internal scaffolding; translate to natural English when the meaning matters to the user — "this is a behaviour change in pricing", not "Classification: business_logic_change". If you catch yourself typing a label, delete it.
Output economy (mandatory)
Spend output tokens on findings, not framing.
- No preamble or self-narration. Spend user-visible output on findings, evidence, and gates — not "I'll first read X, then Y" or "Let me now…"; just do it.
- One question per turn. Don't follow a question with "shall I proceed or clarify first?" — the question IS the gate.
- Don't restate the user's input. They know what they asked.
- Structure only when it earns its place. Section headings only for genuinely multiple sections; tables only when comparing >2 things on >2 axes; otherwise prose is shorter.
- No closing pleasantries. No "happy to dig deeper" / "let me know if you want X" — the next-skill handoff is where routing lives.
The Iron Law
NO QA WORK WITHOUT FIRST DECIDING THE APPROACH.
You may not produce test ideas, scaffolds, plans, reviews, or strategies without first invoking sumo-qa-deciding-approach.
When to Use
This skill is the entry router for every QA-shaped request — "review my changes / is this safe to merge", "how should I test X", "create a test plan", "plan QA for this story", "scaffold the failing tests", "what test data do I need", "audit our test coverage", "design our QA strategy", and similar. It produces no QA output itself: it enforces the Iron Law, sets up the global discipline every sub-skill inherits, then routes to sumo-qa-deciding-approach.
Global discipline (inherited by every sub-skill)
Knowledge authority hierarchy
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.
- 3d ago First seen · 128 lines · 127 tokens per session scan A 8241cbdffe1e
using-sumo-qa is a skill published in the GitHub repository sumithr/sumo-qa (6 stars, last pushed 9d ago), licensed Apache-2.0. It adds 127 tokens to every session and 3,701 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
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…
xcodebuildmcp-structured-output-review
Use when reviewing XcodeBuildMCP structured output schema changes, schema versioning, manifest outputSchema metadata, and JSON fixture compatibility.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
mcp-transport-contract-auditor
Route shaft-mcp transport-contract audits to the canonical playbook.
create-operator
MUST READ before creating or moving any operator (createop, copyop, setopposition, or executepython builds). Required verification, canonical positioning recipe, and error-checking steps.
cortex-automate
Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…