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-planning-qa-rolloutgit 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-planning-qa-rollout)<a href="https://agentmods.dev/skills/sumithr/sumo-qa/sumo-qa-planning-qa-rollout"><img src="https://agentmods.dev/badge/skills/sumithr/sumo-qa/sumo-qa-planning-qa-rollout/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-planning-qa-rollout"><img src="https://agentmods.dev/badge/skills/sumithr/sumo-qa/sumo-qa-planning-qa-rollout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 48 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00101 | $0.02506 |
| Opus 5.5 | $0.00040 | $0.01002 |
| Sonnet 5.5 | $0.00020 | $0.00501 |
| Haiku 4.5 | $0.00010 | $0.00251 |
Grade A, and why
sumo-qa-planning-qa-rollout 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 27d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning a QA rollout
Help the user turn an amorphous QA ask ("we need test coverage for the new refund flow", "Phase 1 of the strategy") into a written plan a fresh agent or teammate could pick up and execute task-by-task — without you in the room.
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
NO EXECUTION FROM THE PLANNER. THE PLAN IS THE DELIVERABLE. The plan must stand alone — readable by someone who wasn't in the conversation, specific enough that a fresh subagent given just one task could execute it without coming back for clarification.
When to Use
sumo-qa-deciding-approach routes here when:
- the work spans 3+ tasks that can be done independently (otherwise: skip planning, route straight to
sumo-qa-implementing-with-tddor similar) - the user said "plan QA for this story" / "plan the test rollout" / "break this into tasks" / "prep this for subagent execution"
sumo-qa-strategisinghas produced a strategy and the user wants to act on Phase 1- the work is going to be picked up by someone other than the planner (handoff)
For a single 30-minute QA task, planning is overhead — go straight to the matching skill.
Checklist
Note on confirmation rhythm: the per-step gates are upper bounds, not
mandatory turn-counts. Per the Confirmation discipline (see using-sumo-qa),
collapse adjacent obvious sections into a single update when the user has
clearly endorsed the trajectory; reserve a structured question for steps
where the choice meaningfully changes the rest of the plan. In particular,
step 6 ("Walk the plan section-by-section, confirm") should be read as: batch
adjacent task groups when the user has already validated the approach — the
goal is to catch mis-shaped tasks early, not to ask permission for each one.
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.
- 27d ago Changed · -2 lines fa3a9731bf25
- 1mo ago Changed · -5 tokens per session b79430d094a7
- 2mo ago First seen · 157 lines · 106 tokens per session scan A 506b611b7400
sumo-qa-planning-qa-rollout is a skill published in the GitHub repository sumithr/sumo-qa (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 101 tokens to every session and 2,506 once invoked, about $0.0004 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
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…
sugar-quality-guardian
Guides an agent to review code for quality, testing, security, and performance before completion. Use when reviewing a pull request, diff, or code change for quality; enforcing test coverage and standards; validating security (injection, auth, hardcoded secrets); assessing code smells and anti-patterns; or producing a…
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
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…
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…