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/bugzy-ai/bugzy/claude-mdgit clone --depth 1 https://github.com/bugzy-ai/bugzyWhat 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 | $0.03348 | $0.03348 |
| Opus 5 | $0.01674 | $0.01674 |
| Sonnet 5 | $0.00670 | $0.00670 |
| Haiku 4.5 | $0.00335 | $0.00335 |
Grade A, and why
bugzy CLAUDE.md 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 2d 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 — 343 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.
Project Overview
Bugzy is an open-source CLI tool that manages AI agent configuration for QA automation. It generates Claude Code configuration files (slash commands, subagents, MCP servers) based on user-selected integrations. The package is designed to be installed globally via npm and run in any project directory.
Development Commands
# Build the project
pnpm build
# Watch mode for development
pnpm dev
# Run all tests
pnpm test
# Run tests in CI mode (single run)
pnpm test:ci
# Type checking (always run before committing)
pnpm type-check
# Lint the code
pnpm lint
# Publish to npmjs
npm publish
Publishing
The package is published to npmjs as a public scoped package (@bugzy-ai/bugzy).
Full Release Process:
- Bump version:
npm version patch|minor|major --no-git-tag-version - Build:
pnpm build - Publish:
npm publish - Commit changes:
git add . && git commit -m "chore: Release vX.X.X" - Push:
git push
Testing
- Use Vitest for all tests
- Test files are located in
tests/directory - Run single test file:
pnpm test tests/path/to/file.test.ts - Tests cover: task generation, command generation, configuration validation, and integration scenarios
Architecture
Core System Design
Bugzy uses a step-based composition architecture:
- Registry System (
src/core/registry.ts): Central coordinator that assembles complete agent configuration from task definitions and project subagents - Task Builder (
src/core/task-builder.ts): Builds dynamic task definitions from composable steps with conditional subagent injection - Generator Pipeline (
src/cli/generators/): Transforms configuration into files (.claude/commands/, .claude/agents/, .mcp.json)
Key Concepts
Task Templates (src/tasks/):
- Define QA automation tasks (8 tasks: explore-application, generate-test-plan, generate-test-cases, run-tests, verify-changes, onboard-testing, handle-message, process-event)
- Each template uses a
steps: TaskStep[]array for composable execution - Steps can be inline content, library references, or conditional on subagent configuration
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.
- 2d ago First seen · 343 lines · 3,348 tokens per session scan A 59bb64877ad2
bugzy CLAUDE.md is an instructions file published in the GitHub repository bugzy-ai/bugzy (5 stars, last pushed 6mo ago), licensed MIT. It adds 3,348 tokens to every session, about $0.0167 per session on Opus 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 2026-08-31.
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.