Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/genai-io/sannpx agentmods add skills/genai-io/san/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/genai-io/san/qa)<a href="https://agentmods.dev/skills/genai-io/san/qa"><img src="https://agentmods.dev/badge/skills/genai-io/san/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/genai-io/san/qa"><img src="https://agentmods.dev/badge/skills/genai-io/san/qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.01235 |
| Opus 5.5 | $0.00034 | $0.00494 |
| Sonnet 5.5 | $0.00017 | $0.00247 |
| Haiku 4.5 | $0.00009 | $0.00123 |
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 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.
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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA — Feature Regression Testing
Run automated and interactive regression tests for a San feature by name.
Arguments
<feature>— Feature name, e.g.agent,cli-startup,loop,session,hook.--interactive— Also run interactive tmux tests (default: automated only).--pane— For interactive tests, split a pane in the current tmux window instead of creating a separate session. Lets the user watch the test live.
Workflow
1. Resolve the feature doc
Look for the feature in this order:
docs/reference/<feature>.md— reference docs, may have Automated Tests and Interactive Tests (tmux) sectionsdocs/packages/2-feature/<feature>.md— feature package docs, has a## Testssection
Read the file. Extract:
- Automated Tests section — the
go testcommands and known test cases (from reference docs). - Interactive Tests (tmux) section — the step-by-step tmux script (from reference docs).
- Tests section — package-level test info from feature docs.
If the feature matches an integration test directory name (tests/integration/<feature>/), add go test ./tests/integration/<feature>/... as a default test command even if the doc doesn't list one.
If the feature cannot be found in any doc path, list all available features (integration test dirs + doc stems from both locations) and ask the user to pick one.
2. Build the binary
Always build first so tests run against the latest code:
make build
If the build fails, stop and report the error — no point running tests against stale code.
3. Run automated tests
Execute every go test command extracted from the feature doc's Automated Tests section, plus the default integration test command if applicable. Capture stdout/stderr and exit codes. Each command is a separate test group.
Record results as:
- PASS — exit code 0
- FAIL — exit code non-zero; include the failure output
4. Run interactive tests (only with --interactive or --pane)
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 · 136 lines · 85 tokens per session scan A 02af8038d4d0
qa is a skill published in the GitHub repository genai-io/san (78 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 1,235 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
tmux-manual-qa
Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.
pi-package-sandbox-test
Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.
agent-browser
Automates browser and Electron app interactions for user-flow validation.
benchmark-validator
Benchmark validation procedure for one assigned benchmark-related target. For optimization EXP- targets, independently classify candidate outcome. For engineering VAL- or legacy engineering targets, prove or disprove the required benchmark/performance assertion.
scrutiny-validator
Adversarial scrutiny procedure for engineering validation assignments. Runs hard-gate commands, reviews the current implementation and evidence integrity against assigned contracts, can use feature-reviewer lanes, and returns per-target verdicts.
user-testing-validator
Real-surface validation coordinator for engineering validation assignments. Exercises assigned assertions through browser, API, CLI, background, generated-artifact, migration/data, public-library, or parity surfaces and returns per-target verdicts with fresh evidence.