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 commands/higoralves/orc/qagit clone --depth 1 https://github.com/HigorAlves/orcWhat 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 | $0.00053 | $0.02484 |
| Opus 5 | $0.00026 | $0.01242 |
| Sonnet 5 | $0.00011 | $0.00497 |
| Haiku 4.5 | $0.00005 | $0.00248 |
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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Bash(curl:*) How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:qa
Run a quality gate before opening a PR. Two modes:
- Code/CLI/library change — run tests, lint, type-check; verify with
orc:verification-before-completion; do a self-review withorc:caveman-review. No browser. - Web change — same as above PLUS browser-driven QA, with a driver chosen per run (Phase 4.1): the
agent-browserCLI via theorc-qa-validatoragent (headless, richest evidence), or the Claude-in-Chrome extension run inline in this session (the user watches the test live in their own browser). Evidence is saved to.orc/<branch>/files/qa/either way.
Arguments
-
--auto[=guided|full]— autopilot level for this run (overridesinteraction_policy; taxonomy inorc:using-orc). Soft-inward gates consult the resolved policy —guidedauto-advances mechanical confirms with a printed one-liner;fullpre-approves them from settled decisions (orc:state-protocol), stopping only on escalation-only conditions. Hard-outward gates are unaffected at every level. -
--web <url>— explicit URL of a running app (skips env provisioning AND the validator's boot path — you're saying it's already up). -
--no-web— force code-only mode even if web files were touched. -
--no-env— skip Docker env provisioning; the validator falls back to its legacy dev-script boot. -
--driver agent-browser|chrome— pick the browser driver up front and skip the Phase 4.1 prompt.agent-browser= headless CLI viaorc-qa-validator(criterion-anchored annotated screenshots, WebM recording whenffmpegis installed, HAR, network mocking).chrome= Claude-in-Chrome extension, run inline so the user watches live in their real browser (real sessions/extensions, GIF recording). -
The remaining argument is the feature description (used to scope golden-path testing).
Workflow
Phase 0 — Detect context
!orc-workspace-detect --banner
Context is injected above (ORC_* vars are exported for any Bash you run — do not re-run detection).
In workspace mode, resolve targetRepos from flags or via AskUserQuestion. Default in workspace mode is to verify every repo in the active workspace session's repos array. The web-QA target is always one repo — pick from the plan's "Repo touchpoints" section (the entry that owns the web surface) or prompt if ambiguous.
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 · 138 lines · 53 tokens per session scan A 8418cca6fb7a
qa is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 6d ago), licensed MIT. It adds 53 tokens to every session and 2,484 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other commands, from other repositories
qawolf-cli
Manage QA Wolf through the qawolf CLI. Use when asked to create, update, or list coverage requests, bug reports, or maintenance reports; start a run of flows or tags on the QA Wolf platform or read a run's results; list, set, or delete environment variables; manage environments, flows, or tags; request automation of…
live-verify
Two-part gate for gflow-cli feature work — pre-flight state check at the start, live-verification against real Flow before claiming done.
buildable-preview
Render the running prototype in a headless browser, screenshot it, and catch runtime/visual errors.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
visual-verify
Use Playwright MCP to visually verify the UI that was just built or modified.