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 instructions/dpaul20/qacito/claude-mdgit clone --depth 1 https://github.com/dpaul20/qacitoWrote 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/instructions/dpaul20/qacito/claude-md)<a href="https://agentmods.dev/instructions/dpaul20/qacito/claude-md"><img src="https://agentmods.dev/badge/instructions/dpaul20/qacito/claude-md.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 | $0.01590 | $0.01590 |
| Opus 5 | $0.00795 | $0.00795 |
| Sonnet 5 | $0.00318 | $0.00318 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade B, and why
qacito CLAUDE.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
> **Note:** `install.mjs` writes to `~/.claude/settings.json` which Claude Code does not read for MCP servers. Always use `claude mcp add` instead. MCPs are stored in `~/.claude.json` (user scope) or `.mcp.json` (project How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
# Build (TypeScript only)
npm run build
# Build mcp-app → dashboard → TypeScript (in order)
npm run build:all
# Run MCP server (stdio transport)
npm start
# Run MCP server (HTTP transport on port 4712)
npm run start:http
# Run all tests (unit + integration)
npx playwright test
# Run a single test file
npx playwright test src/tools/run-tests/retry-tracker.test.ts
# Build only the MCP App React bundle
npm run build:mcp-app
# Build .mcpb distributable
npm run build:mcpb
# Run headless batch orchestrator (CI mode, requires ANTHROPIC_API_KEY)
npm run batch -- --project /path/to/project --output report.json
# Register QAcito as MCP server (global — available in all projects)
claude mcp add --scope user qacito -- node "$(pwd)/dist/server/index.js"
# Register QAcito as MCP server (project-only — writes .mcp.json in the target project)
claude mcp add --scope project qacito -- node "/absolute/path/to/QAcito/dist/server/index.js"
# Verify registration and connection
claude mcp list
# (Legacy) TUI wizard — writes to settings.json, does NOT register the MCP correctly
node scripts/install.mjs
Note:
install.mjswrites to~/.claude/settings.jsonwhich Claude Code does not read for MCP servers. Always useclaude mcp addinstead. MCPs are stored in~/.claude.json(user scope) or.mcp.json(project scope).
Architecture
QAcito is an MCP server with a strict separation: Claude decides, QAcito executes. The server never interprets results or chooses what to test — that's Claude's job.
Transports
src/server/index.ts boots two layers before accepting MCP connections:
- Dashboard server (
src/dashboard-server/) — Express + WebSocket on a dynamic port (50000–59999). Must start first because tools depend on its run-store and WS broadcaster. - MCP transport — stdio (default) or HTTP (
QACITO_HTTP_PORT=4712).
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 · 131 lines · 1,590 tokens per session scan B d681736a15bf
qacito CLAUDE.md is an instructions file published in the GitHub repository dpaul20/qacito (0 stars, last pushed 11d ago), licensed MIT. It adds 1,590 tokens to every session, about $0.0080 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.