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/sushichan044/cc-hooks-ts/agents-mdgit clone --depth 1 https://github.com/sushichan044/cc-hooks-tsWrote 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/sushichan044/cc-hooks-ts/agents-md)<a href="https://agentmods.dev/instructions/sushichan044/cc-hooks-ts/agents-md"><img src="https://agentmods.dev/badge/instructions/sushichan044/cc-hooks-ts/agents-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 5.1 | $0.00505 | $0.00505 |
| Opus 5 | $0.00253 | $0.00253 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
cc-hooks-ts AGENTS.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 6d 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 — 60 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
A TypeScript library for defining Claude Code hooks with type safety. Provides runtime validation and strongly-typed definitions for hook configurations.
Development Commands
YOU MUST RUN vp check && vp test --run && vp pack to run all quality checks before completing any tasks.
vp check- Run all checks (lint, format, typecheck)vp check --fix- Auto-fix lint and format issuesvp test --run- Run testsvp pack- Build
How to follow the upstream changes
See the same section in README.md to follow upstream changes from @anthropic-ai/claude-agent-sdk.
Repository Structure
Source Code (src/)
- Root files - Core library APIs (hook definition, execution, context)
hooks/- Hook event definitions, input validation schemas, output typesutils/- Shared utility functions for strings, types, and validation
Other Directories
docs/- Documentation and guidesdist/- Build output (generated)
When to Touch What
| Goal | Where to Work |
|---|---|
| Add new hook event / Backport upstream hook type change | src/hooks/ |
| Modify input validation | src/hooks/input/ |
| Change output types | src/hooks/output/ |
| Update tool schema definitions | src/index.ts |
| Add utility functions | src/utils/ |
| Update documentation | docs/ |
Coding Goodies
Vitest
- Import vitest API explicitly
- Prefer
describe(target) { it(behavior) }structures overtest()
Type System Design Philosophy
- Convergence Point Validation: Test complex conditional type chains at final output with concrete literal types
- Boundary Design: Validate TypeScript inference at abstract→concrete type transformation points
- Contract-Focused: Test usage patterns (contract boundaries) rather than implementation details
- Inference Proof: Prove complex type operation combinations with concrete type results
- Resilience Design: Choose validation points that resist internal implementation changes
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.
- 6d ago First seen · 60 lines · 505 tokens per session scan A 736ce88c40d1
cc-hooks-ts AGENTS.md is an instructions file published in the GitHub repository sushichan044/cc-hooks-ts (39 stars, last pushed yesterday), licensed MIT. It adds 505 tokens to every session, about $0.0025 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
vscode design-philosophy.instructions.md
VS Code design philosophy — the shared Values→Principles→Moves vocabulary for reasoning about UI in design terms rather than raw pixels. Use when creating, editing, or reviewing any visual surface (CSS, DOM, theming, icons, motion). Name the value/principle before reaching for a token.
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
retry-axios GEMINI.md
Gemini CLI instructions for JustinBeckwith/retry-axios, covering project: retry-axios, project overview, building and running, dependencies and commands.
huly-mcp CLAUDE.md
Claude Code instructions for dearlordylord/huly-mcp, covering project instructions, design principle: llm-first api, project harness (copy to new projects), package manager and verification.
plate CLAUDE.md
Claude Code instructions for udecode/plate, a project described as: Rich-text editor with AI and shadcn/ui.
sofagent GEMINI.md
Gemini CLI instructions for KongFangXun/sofagent, covering gemini.md · sofagent gemini cli 适配（薄挂载）, 会话开始时按序加载（四层加载链）, 审计强制（平台无关） and 连接 mcp server.