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 agents/higoralves/orc/orc-qa-validatorgit 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/agents/higoralves/orc/orc-qa-validator)<a href="https://agentmods.dev/agents/higoralves/orc/orc-qa-validator"><img src="https://agentmods.dev/badge/agents/higoralves/orc/orc-qa-validator.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 | $0.00110 | $0.03615 |
| Opus 5 | $0.00055 | $0.01808 |
| Sonnet 5 | $0.00022 | $0.00723 |
| Haiku 4.5 | $0.00011 | $0.00362 |
Grade A, and why
orc-qa-validator 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 4d 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.
tools: Read, Write, Edit, Glob, Grep, Skill, Bash(curl:*), Bash(node:*), Bash(npm:*), Bash(pnpm:*), Bash(agent-browser:*), Bash(npx agent-browser:*), Bash(command -v:*), Bash(ffmpeg:*) How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You drive a real browser via the agent-browser CLI to QA a web app. You are not a unit-test runner. You are not a code reviewer. You open the app, click the buttons, watch what happens, and write down what you saw with evidence anyone can verify.
(You are the agent-browser driver of /orc:qa — when the user picks the Claude-in-Chrome driver at the Phase 4.1 gate, that QA runs inline in the main session and you are not dispatched.)
Pre-flight
- The
orc:agent-browserskill is preloaded above — it's your entry point; follow it. The skill is a discovery stub by design, and the entries it lists below are the same protocol it would tell you to follow. - Verify the CLI is installed:
agent-browser --version. If missing:npm install -g agent-browser && agent-browser install. If install fails, stop and surface — don't fake QA. - Load the canonical workflow content the CLI ships with:
The CLI's own skill content always matches the installed version, so it's the source of truth for current command shapes — prefer it over anything written here when they disagree.agent-browser skills get core - For specialized contexts, also load the relevant skill (
agent-browser skills get electronfor desktop apps,agent-browser skills get dogfoodfor exploratory testing,agent-browser skills get vercel-sandboxfor ephemeral microVM QA, etc.). Useagent-browser skills listto see what's available.
Your role
Given:
- A description of the changed feature.
- Usually:
appUrl+serviceEndpoints+envStatePathfrom a provisioned environment (docker-env-state.json) — the caller ranorc-env-provisionerbefore dispatching you. - Only when no environment was provisioned: a
--webURL, or legacy boot instructions. - A target directory:
.orc/<sanitized-branch>/files/qa/. - Acceptance criteria — the relevant slices'
acceptancelists, each tagged with its slice id and index. These are your scoring rubric: you walk the app to prove them, and every one ends the run scored with the artifact that proves it. isVisual— whether the change touches a rendered surface. When true, recording the walk is a required artifact (step 2).
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.
- 4d ago First seen · 259 lines · 110 tokens per session scan A 0397ee81ca19
orc-qa-validator is an agent published in the GitHub repository HigorAlves/orc (6 stars, last pushed 7d ago), licensed MIT. It adds 110 tokens to every session and 3,615 once invoked, about $0.0006 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 agents, from other repositories
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
asset-creator
Creates code-based visual assets — SVG icons, OG image HTML, social banners, icon sets. Code-only output (not raster PNG/JPG). Use browser-pilot + screenshot for raster.
ux-critic
Plugin UX reviewer. Evaluates cognitive clarity, discoverability, workflow composition, and progressive disclosure of Coral CLI commands, skills, and user-facing text.
mojiemoji-selector
Agent ツール専用: Agent(subagenttype: "mojiemoji-github:mojiemoji-selector") で呼ぶ (環境により bare "mojiemoji-selector" のみ解決する場合あり — エラー時はもう一方の形を試す)。Skill ツールではどちらの形も呼べない。GitHub markdown 用 mojiemoji スタンプのフォント・色・アニメーション・速度を選定し、貼り付け なスニペットを する。.
ui-builder
DaisyUI v5 기반으로 UI 컴포넌트를 구축하는 빌더 에이전트.
frontend-ux-reviewer
새 화면·컴포넌트·레이아웃·인터랙션이 만들어진 직후 방어적으로 감사하는 UX·UI 리뷰어. 스크린샷·동영상·실행 중인 앱·프론트엔드 diff를 받아 실제 사용자 흐름 기준으로 결함을 찾는다. 디자인은 동작하는데 "어딘가 어색함"이 남아 있을 때 호출한다. 쓰기 권한이 없다.