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/panda850819/verbs/qanpx skills add panda850819/verbs --skill qagit clone --depth 1 https://github.com/panda850819/verbsWrote 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/panda850819/verbs/qa)<a href="https://agentmods.dev/skills/panda850819/verbs/qa"><img src="https://agentmods.dev/badge/skills/panda850819/verbs/qa.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.00885 |
| Opus 5 | $0.00033 | $0.00443 |
| Sonnet 5 | $0.00013 | $0.00177 |
| Haiku 4.5 | $0.00007 | $0.00089 |
Grade A, and why
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA
QA is the evidence protocol: structured assertions a merge decision can trust, not a test-writing tutorial.
Context
Read the ## verbs config from CLAUDE.md or AGENTS.md; resolve
{learnings_dir} (default docs/learnings) and search related type: pitfall
entries using lib/learning-format.md. Read a matching brief from
docs/briefs/. Bind the intent source and assign stable
AC-1, AC-2, ... identifiers to its acceptance criteria. Without an issue,
brief, or explicit goal, report INTENT GAP; behavior alone cannot prove intent.
Plan
Produce ONE numbered list of action → expected result checks: core user flows first, then error/empty/loading states, edge inputs, double submit, Escape, keyboard-only navigation, mobile viewport, and console errors. For UI work, also include 320px reflow, 200% zoom, every shipped locale and reduced-motion behavior where motion exists. Name the width, zoom, locale and state in each check instead of treating "mobile" as coverage. If the flows are unclear, ask what to test.
Test
Run small changes directly. Use isolated browser workers only for 3+ groups when
session isolation is proven; otherwise run sequentially. Give each worker its
numbered tests, the assertion protocol below, and a step budget (~25 targeted / ~40 full page / ~75 multi-page);
at budget accept partial results with STEP_SKIP; the main agent merges and
summarizes worker results, and never share a browser session.
Every test step MUST emit one marker:
STEP_PASS|<step-id>|<evidence>
STEP_FAIL|<step-id>|<expected> -> <actual>
STEP_SKIP|<step-id>|<reason>
Use the strongest available verification in this order: deterministic evaluation,
accessibility snapshots, before/after comparison, and screenshots only where the
tree cannot prove the property. A
STEP_FAIL always gets a screenshot and a [BUG] report per
lib/qa-evidence-format.md. End with:
Tests: N | Passed: N | Failed: N | Skipped: N | Pass rate: N%
Acceptance evidence handoff
What ships with it
2 files 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.
- 3d ago First seen · 93 lines · 66 tokens per session scan A 5be54cae727d
qa is a skill published in the GitHub repository panda850819/verbs (5 stars, last pushed 11d ago), licensed MIT. It adds 66 tokens to every session and 885 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
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
playwright-validation
Use when validating UI changes in a branch require Playwright E2E testing. Reviews branch changes, validates UI with Playwright MCP, and adds missing test cases.
feature-walkthrough
Autonomously test the running binance-trading-bot app in a real browser. The agent drives the browser itself via the Playwright MCP - logs in, looks at each screen, and works through every feature end-to-end like a real operator, finding and fixing bugs. Use when asked to test the app, smoke-test or walk through the…
playwright-screen-recording
Record browser test videos with Playwright for PR review and bug fix verification.
firecrawl-build-scrape
Integrate Firecrawl /scrape into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer this skill over broader crawl patterns when the feature is page-level.
browser-smoke-review
Use browser automation to review docs pages, preview URLs, rendered output, or web-facing fallow surfaces. Use when the user wants a screenshot-based review, browser smoke test, docs site check, or preview deployment inspection.