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/codeworksh/codework/claude-mdgit clone --depth 1 https://github.com/codeworksh/codeworkWhat 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 | $0.01022 | $0.01022 |
| Opus 5 | $0.00511 | $0.00511 |
| Sonnet 5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
codework 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.
This is a copy
95% identical to codework AGENTS.md — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal Preference
TypeScript
- Never use
anyunless 100% necessary or specifically instructed. - Use effect only if the project uses effect or specifically instructed, use effect reference repository for latest architecture patterns.
Commands
- Don't run dev server commands (e.g
bun run dev,pnpm run dev) - assume it's already running. - Don't run build commands unless specifically told to.
- Focus on checking commands like
bun run typecheck,pnpm run check,bun run lint, etc.
Package Managers
- Use
pnpm,vp - vite plusif the project already uses it, otherwise usepnpm - Never use
npmoryarn
Tech Stack Preference
When uncertain, prefer: Effect, Tailwind, TypeScript, React, Clerk, TanStack, Vercel, Vite.
Code Style
- Always strive for concise, simple solutions.
- If a problem can be solved in a simpler way, propose it.
- No pre-mature optimizations, propose if required.
- Use single word filename whenever possible otherwise split into kabab-case(only if no options).
General Preferences
- If asked to do too much work at once, stop and state that clearly.
- If computer use is helpful for completing or verifying work, shell out to gpt-5.5 with Codex for it
- Avoid defensive future-facing design. This leads to pre-mature assumptions which are never true.
Maintainability
Long term maintainability is a core priority. If you add new functionality, first check if there is shared logic that can be extracted to a separate module. Duplicate logic across multiple files is a code smell and should be avoided. Don't be afraid to change existing code. Don't take shortcuts by just adding local logic to solve a problem.
Package Roles
packages/aikit- Low level SDK that provides unified LLM API for multiple LLM providers.packages/harness- Effect powered main Agent Harness application, usespackages/aikitunder the hood.packages/utils- Shared support utilities used bypackages/aikitandpackages/harness..scratch/packages- Local, ignored reference archive for packages that are no longer developed.
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 · 82 lines · 1,022 tokens per session scan A 17860695040e
codework CLAUDE.md is an instructions file published in the GitHub repository codeworksh/codework (23 stars, last pushed 4d ago), licensed MIT. It adds 1,022 tokens to every session, about $0.0051 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to codework AGENTS.md, differing in 10 lines, and is treated as a copy.
Other instructions, from other repositories
keen-code AGENTS.md
Instructions for mochow13/keen-code, covering keen code, important guidelines, architecture and permission system.
vix AGENTS.md
AGENTS.md instructions for get-vix/vix, covering agents.md, project overview, architecture, instance control channel and development commands.
keen-code CLAUDE.md
Instructions for mochow13/keen-code, a project described as: A context-aware terminal-based coding agent written in Go. Supports multiple-providers, MCPs, Subagents, Agent Skills, controllable tool output retention, hashline edits, and more.
dev-agent-skills CLAUDE.md
Instructions for fvadicamo/dev-agent-skills, covering claude.md, project overview, architecture, key file: marketplace.json and skill anatomy.
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
codevira CLAUDE.md
Instructions for sachinshelke/codevira, covering codevira — persistent project memory, when to call which codevira tool, at the start of every session, before modifying any file and before adopting a pattern, library, or naming convention.