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-reviewing-before-mergegit 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-reviewing-before-merge)<a href="https://agentmods.dev/skills/sumithr/sumo-qa/sumo-qa-reviewing-before-merge"><img src="https://agentmods.dev/badge/skills/sumithr/sumo-qa/sumo-qa-reviewing-before-merge/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-reviewing-before-merge"><img src="https://agentmods.dev/badge/skills/sumithr/sumo-qa/sumo-qa-reviewing-before-merge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Data Exfiltration · line 234 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- medium Agent Snooping · line 207 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00084 | $0.17084 |
| Opus 5 | $0.00042 | $0.08542 |
| Sonnet 5 | $0.00017 | $0.03417 |
| Haiku 4.5 | $0.00008 | $0.01708 |
Grade A, and why
sumo-qa-reviewing-before-merge 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 11d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing before merge
Help the user decide whether a change is safe to ship by walking the review one section at a time: explore the diff, surface what was found, name the risks, run the verification, deliver the verdict. The user has product context (was this a deliberate behaviour change? is this consumer used externally?) the AI can't infer from the diff alone — surface it through questions, don't assume it.
Announce at start: "Reviewing the diff against fresh test evidence."
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"; this includes the raw keys of any loaded change-rules file — cite the rule in plain English, e.g. "the documented-inventory rule", never by echoing its YAML key), 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
NEVER CLAIM SAFE-TO-MERGE WITHOUT FRESH VERIFICATION EVIDENCE. "All tests pass" is necessary but not sufficient — every named risk must also have a passing test covering it.
Evidence-backed gate reporting
Every gate claim you surface — the suite verdict, each named risk's coverage, the safe-to-merge call — carries a status (passed / failed / skipped / blocked / unverified) and, unless skipped or unverified, cites the ONE observed evidence item backing it by source (command, tool_call, file_read, user_fact, external_ci, manual_observation). Citing means NAMING the source and quoting the observation — for the suite verdict, label the source type and quote the verification command verbatim with its counts, e.g. Evidence (command): $ pytest tests/auth -q → 42 passed, 2 skipped. Test names or counts alone, with no labeled source behind them, do NOT count as a cite. A passed / failed / blocked claim with no cited source is an overstatement; unverified is the honest state when nothing was observed this turn. SAFE TO MERGE is a passed safe-to-merge gate — unreachable while any gate is failed / blocked / unverified (step 10, restated as a status). Keep it compact: a status word + a short source cite per line, never a second dump.
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.
- 11d ago First seen · 275 lines · 84 tokens per session scan A 8f9062840477
sumo-qa-reviewing-before-merge is a skill published in the GitHub repository sumithr/sumo-qa (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 84 tokens to every session and 17,084 once invoked, about $0.0004 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
trace-mcp-refactoring
Safe refactoring workflow using trace-mcp — assess risk, find candidates, check impact, and rename symbols across all files without missing import sites or cross-file references.
m1nd-first
Use when investigating a repository, searching for implementation, reviewing changes, working from specs/docs, or preparing a risky code change in an environment where m1nd is available. This doctrine makes m1nd the first investigative layer before grep, glob, or manual file reads, except when the task is pure…
review-thread
Record review verdicts and run the StateNote review thread on an agent-operation instance — every ReviewRequest verdict is one atomic batch-direct-write that advances status and co-writes a reviewnote explaining why, and findings are corrected by appending notes rather than editing them.
audit-architecture
Audit module coupling, cohesion, hidden dependencies, and design smells. Use when conducting architecture reviews, evaluating design decisions, or identifying structural tech debt.
find-bugs
Locate likely bug locations in code.
review
Assess the blast radius of a change and review a diff — what it touches, what could break, which tests to run, and the prior decisions behind it. Use before a refactor, rename, or signature change, and when reviewing a pull request or your own uncommitted diff.