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/yu-iskw/coding-agent-fabric/claude-mdgit clone --depth 1 https://github.com/yu-iskw/coding-agent-fabricWrote 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/yu-iskw/coding-agent-fabric/claude-md)<a href="https://agentmods.dev/instructions/yu-iskw/coding-agent-fabric/claude-md"><img src="https://agentmods.dev/badge/instructions/yu-iskw/coding-agent-fabric/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 | $0.01353 | $0.01353 |
| Opus 5 | $0.00677 | $0.00677 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
coding-agent-fabric 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 4d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeScript Monorepo - Claude Code Memory
Project Overview
This is a production-ready TypeScript monorepo template using modern tooling:
- Package Manager: pnpm (with workspace support)
- Runtime: Node.js (see
.node-versionfor current version) - Build System: tsc / pnpm
- Linting/Formatting: Trunk (manages ESLint, Prettier, and more)
- Testing: Vitest
- CI/CD: GitHub Actions
Quick Commands
pnpm install # Install all dependencies
pnpm build # Build all packages
pnpm test # Run all tests via Vitest
pnpm lint # Run all linters via Trunk
pnpm format # Auto-format code via Trunk
pnpm clean # Clean build artifacts
Code Style
- Use TypeScript for all code
- Follow project ESLint/Prettier configuration (managed via Trunk)
- Use functional programming patterns where appropriate
- Use
PascalCasefor classes/interfaces,camelCasefor functions/variables - Use
kebab-casefor file names (e.g.,user-service.ts)
Testing
- Write tests in
tests/or alongside source files as*.test.ts - Use Vitest for unit and integration tests
- Aim for high test coverage on core logic
- Run
pnpm testbefore committing
Git Workflow
- Create feature branches from
main - Run
pnpm lint && pnpm testbefore commits - Commit messages:
type(scope): description(e.g.,feat(ui): add new button component) - Types: feat, fix, docs, style, refactor, test, chore
- Record changes using the
manage-changelogskill whenchangieis available
Architecture
- Source code in
packages/*orsrc/(depending on package structure) - Development scripts and shared config in root
- CI/CD workflows in
.github/workflows/ - Claude Code configuration in
.claude/ - Document significant design decisions as Architecture Decision Records (ADRs) in
docs/adr; use themanage-adrskill whenadris available
Common Gotchas
- Always use
pnpminstead ofnpmoryarn - Trunk manages tool versions hermetically - don't install linters globally
- The
pnpm-lock.yamlfile is committed for reproducibility - don't gitignore it - Run
trunk installif linters report missing tools
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.
- 4d ago First seen · 120 lines · 1,353 tokens per session scan A 10be1736b733
coding-agent-fabric CLAUDE.md is an instructions file published in the GitHub repository yu-iskw/coding-agent-fabric (1 stars, last pushed 19d ago), licensed Apache-2.0. It adds 1,353 tokens to every session, about $0.0068 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
hop AGENTS.md
Instructions for amittamari/hop, covering agent map, start here, what this repo builds, working rules and common commands.
webfetch-camouflage-mcp AGENTS.md
AGENTS.md instructions for tianhuil/webfetch-camouflage-mcp, covering rules for python repos, general, coding style and validation.
hop CLAUDE.md
Instructions for amittamari/hop, a project described as: Fast full-text search and resume for coding-agent sessions.
cursor-handbook CLAUDE.md
Claude Code instructions for girijashankarj/cursor-handbook, covering claude.md — instructions for claude, project, critical rules, token efficiency (most important) and security (critical).
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.
agent-rulescope AGENTS.md
AGENTS.md instructions for 13624725933/agent-rulescope, a project described as: See exactly which instructions your coding agent inherits. Scan AGENTS.md, CLAUDE.md, Cursor and Copilot rules.