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/copilot-instructionsgit 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/copilot-instructions)<a href="https://agentmods.dev/instructions/sushichan044/cc-hooks-ts/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/sushichan044/cc-hooks-ts/copilot-instructions.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 | $0.00814 | $0.00814 |
| Opus 5 | $0.00407 | $0.00407 |
| Sonnet 5 | $0.00163 | $0.00163 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
cc-hooks-ts copilot-instructions.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 5d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Code Review Instructions
cc-hooks-ts is a TypeScript library that defines Claude Code hook types with runtime validation via valibot. It tracks upstream @anthropic-ai/claude-agent-sdk and Claude Code versioning. The published surface is the source of truth for downstream type-safe hook authors.
When reviewing PRs, prioritize the checks below. Cite file paths and approximate line locations. Apply each check whenever its trigger fires. If no trigger fires, post no comment.
1. Runtime dependency range vs API usage drift
Trigger: the diff adds a call, named import, or member access for a symbol from a package listed under dependencies in package.json (NOT devDependencies, NOT JS / TS built-ins, NOT Node.js core), AND package.json is NOT modified in the same diff.
Action: ask the author to verify the declared range covers the version that introduced the symbol. The lockfile (pnpm-lock.yaml) may resolve a newer version locally so tests pass, but consumers can resolve any in-range older version and hit TypeError: <symbol> is not a function at import time.
2. Hook contract parity with upstream and test coverage
Trigger: the diff makes a semantic change (added, removed, renamed, or restructured field, type, schema entry, or event key) in any of:
- an input schema in
src/hooks/input/schemas.ts - the hook event listing in
src/hooks/event.ts - an output type under
src/hooks/output/ - the
ToolSchemainterface or input/output re-exports insrc/index.ts
Comment-only, JSDoc-only, or formatting-only edits to these files do not trigger this check.
Action: confirm BOTH —
(a) Test coverage: a *.test-d.ts or *.test.ts exercises the changed surface, either added in this diff or already covering the field/type. If neither, flag.
(b) Upstream justification: the PR description, commit message, or linked PR/issue references an @anthropic-ai/claude-agent-sdk version, Claude Code version, or specific upstream change. If absent, request it.
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.
- 5d ago First seen · 50 lines · 814 tokens per session scan A f730001b5f29
cc-hooks-ts copilot-instructions.md is an instructions file published in the GitHub repository sushichan044/cc-hooks-ts (39 stars, last pushed today), licensed MIT. It adds 814 tokens to every session, about $0.0041 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.
solo copilot-instructions.md
Copilot instructions for hiero-ledger/solo, covering github copilot instructions for hiero-ledger/solo and highest-frequency rules.
plate CLAUDE.md
Claude Code instructions for udecode/plate, a project described as: Rich-text editor with AI and shadcn/ui.