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/orcWrote 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/commands/higoralves/orc/qa)<a href="https://agentmods.dev/commands/higoralves/orc/qa"><img src="https://agentmods.dev/badge/commands/higoralves/orc/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 | $0.00053 | $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 7d 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
verify-ui
Verify UI changes in the running Graft plugin via Chrome DevTools MCP.
use-isolated-browser
Use or explain the client-owned isolated Browser tool.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
t800-onboard
Для чата с новичками. Показывает, что настроено в Cursor (global + local), и что умеет отдел T-800.
triage
Triage review findings one by one — present pending TODOs for user decision (approve, skip, modify).