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/kbwo/ccmanager/claude-mdgit clone --depth 1 https://github.com/kbwo/ccmanagerWhat 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 | $0.00595 | $0.00595 |
| Opus 5 | $0.00298 | $0.00298 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
ccmanager 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 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.
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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/holds all TypeScript sources; UI lives insrc/components/, domain logic insrc/services/, shared hooks insrc/hooks/, and utilities/constants in their respective folders.- Tests sit beside the code they cover (e.g.,
Menu.tsxandMenu.test.tsx), enabling focused updates. - Built artifacts compile into
dist/; keep changes out of version control. - Long-form notes and design references live under
docs/; sync any behavior changes here when relevant.
Build, Test & Development Commands
bun run devlaunches TypeScript in watch mode for rapid feedback.bun run buildproduces release-ready output indist/.bun run startexecutes the compiled CLI (dist/cli.js) for manual smoke tests.bun run lint,bun run lint:fix, andbun run typecheckenforce style and typing before review.bun run testruns the Vitest suite once; combine withbun run prepublishOnlybefore publishing to exercise the full pipeline.
Coding Style & Naming Conventions
- Follow the shared Prettier profile (
@vdemedes/prettier-config); formatting issues surface as ESLint errors. - Use modern TypeScript/React patterns, avoiding
any(rule enforced) and preferring explicit types for side-effectful functions. - Components and Effect-style services use PascalCase filenames; hooks start with
use. - Keep TUI prompts and commands in
constants/andservices/rather than inline JSX. - Prefer dependency-free helpers in
utils/so the CLI stays fast to load. - use logger class instead of console. e.g.
logger.info("This is info level log");
Testing Guidelines
- Write Vitest unit tests alongside new files (
*.test.tsor*.test.tsx); mirror the folder containing the behavior. - Use Ink Testing Library utilities for interactive components; stub terminal state as needed.
bun run testoutputs coverage summaries (text, JSON, HTML undercoverage/); maintain or improve coverage when changing core flows.- Name test suites after the component or service under test for easy grepping.
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 · 35 lines · 595 tokens per session scan A c9f12892840e
ccmanager CLAUDE.md is an instructions file published in the GitHub repository kbwo/ccmanager (1,229 stars, last pushed 3d ago), licensed MIT. It adds 595 tokens to every session, about $0.0030 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 2026-08-30.
Other instructions, from other repositories
AionUi AGENTS.md
AGENTS.md instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.
run-gemini-cli GEMINI.md
Instructions for google-github-actions/run-gemini-cli, covering guidelines for developing this github action, core principles for this action and your role in development.
security GEMINI.md
Instructions for gemini-cli-extensions/security, covering standard operating procedures: security analysis guidelines, persona and guiding principles, skillset: permitted tools & investigation, skillset: sast vulnerability analysis and 1.1. hardcoded secrets.
obsidian-llm-hub CLAUDE.md
Instructions for takeshy/obsidian-llm-hub, covering claude.md, project overview, build commands, version bumping and architecture.
jules GEMINI.md
Instructions for gemini-cli-extensions/jules, covering jules extension, command: /jules, activation and response, starting a jules task and jules-related queries.
maestro-orchestrate GEMINI.md
Instructions for josstei/maestro-orchestrate, covering maestro techlead orchestrator, startup checks, gemini cli integration constraints, context budget and settings reference.