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 arcee-ai/nac --skill qagit clone --depth 1 https://github.com/arcee-ai/nacWrote 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/arcee-ai/nac/qa)<a href="https://agentmods.dev/skills/arcee-ai/nac/qa"><img src="https://agentmods.dev/badge/skills/arcee-ai/nac/qa/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/arcee-ai/nac/qa"><img src="https://agentmods.dev/badge/skills/arcee-ai/nac/qa.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 56 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 | $0.00100 | $0.05575 |
| Opus 5.5 | $0.00040 | $0.02230 |
| Sonnet 5.5 | $0.00020 | $0.01115 |
| Haiku 4.5 | $0.00010 | $0.00558 |
Grade A, and why
qa scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
compatibility: Requires a local unsandboxed Git checkout, Rust and web build tools, curl, and rootless Podman. How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NAC quality assurance
Run adversarial, evidence-backed QA against one requested committed revision. Exercise the live branch-built server, not only unit tests. Preserve every worker's findings in independent ignored reports, then summarize the complete pass.
This workflow tests; it does not fix. Never edit source, dependency files, generated assets, repository configuration, issues, or pull requests during a QA pass.
Input and roles
n is the number of QA test workers. Accept one positive integer and default to 4. A caller-supplied value means exactly that many test workers, not a maximum or aspiration. Reject zero, negative, non-integer, or locally unsupportable values with concrete capacity evidence; never reduce n silently.
Caller requests about focus or duration are ordinary test context, not additional formal parameters.
The process's starting directory is only a place from which to resolve the requested revision. Its branch, staged files, unstaged files, and untracked files are never infrastructure failures by themselves. Setup must select an existing clean worktree at the target commit or create one, change its working directory to that root, and run the pass there. Workers and aggregate must likewise change to the setup-defined root before inspecting Git or running commands.
The top-level controller is not a QA test worker. In nac it sees this catalog description but cannot read or write files; it must use this exact choreography:
- Dispatch
qa/setupwithskills: ["qa"]andmode=setup,n, the caller's requested revision or PR, and the caller's complete scope/focus context. - Read the retained setup episode. It must contain the absolute execution-worktree root, pass root, source SHA, binary, and
ndistinct assignment contracts. - Dispatch exactly those
ntest workers together in one parallel wave. Copy every setup contract verbatim—especiallyrepo_root,slot,scope,report, andevidence—then addskills: ["qa"],qa/setupas a source thread, the setup-provenpodman_mode,XDG_RUNTIME_DIRonly for local mode, and ephemeral connection fields only for remote mode. Never rename, repartition, or “improve” assignments afterRUN.jsonexists. - After all
nfinish, dispatchqa/aggregatewithskills: ["qa"],mode=aggregate, the setup-definedrepo_root, exact slots,qa/setup, every test worker that produced a retained episode, and explicit dispatch outcomes for workers without episodes. A failed or timed-out worker cannot be named as a source thread. - Return the aggregate conclusion. Never substitute one all-purpose QA worker for this topology.
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.
- 1mo ago First seen · 289 lines · 100 tokens per session scan A e7d05b99696f
qa is a skill published in the GitHub repository arcee-ai/nac (283 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 5,575 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -…
vibe-behavioral-test-capture
Builds an executable safety net of characterization tests by integrating browser flow recording, API payload snapshotting, DOM state captures, network traces, and mock fixture generation.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.