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/tyrchen/rust-lib-template/claude-mdgit clone --depth 1 https://github.com/tyrchen/rust-lib-templateWhat 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 | $0.05226 | $0.05226 |
| Opus 5 | $0.02613 | $0.02613 |
| Sonnet 5 | $0.01045 | $0.01045 |
| Haiku 4.5 | $0.00523 | $0.00523 |
Grade A, and why
rust-lib-template 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.
This is a copy
100% identical to rust-lib-template AGENTS.md — 0 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{{ project-name }}
IMPORTANT: Never enter plan mode automatically!!! Never enter plan mode automatically!!!
Core Principles
Completion Discipline
- Do Not Stop Early: If the user's requested outcome is not fully complete, do not stop at a draft, partial pass, or "good enough" result. Continue reviewing and improving until the request is genuinely handled or a concrete blocker requires user input.
- Polish Bar: Before declaring work complete, ask whether the result is fully polished, concrete, correct, complete, and elegant. If there is doubt, review the work again and update it.
- Honest Status: Do not claim a task is finished when it is only a first pass, scaffold, or partial draft. State the remaining gaps and keep working unless the user explicitly asks to pause.
Code Quality
- SOLID and DRY Principles: Maintain clean, maintainable code following SOLID and DRY principles
- No Incomplete Code: Never write TODO comments or temporary solutions. If you encounter such a situation:
- Stop the current task
- Review the problem globally
- Rethink the design and identify the best alternative solutions
- Proceed with the complete solution
- Thorough Analysis: Always perform a comprehensive review and analysis of the problem before starting work
- Do not suppress dead code, remove them; Unless explicitly requested, do not go through deprecation process, just remove the code that is no longer needed.
Development Workflow
- Latest Dependencies: Always search the web for the latest dependencies or helm charts or resources and their current usage patterns. If doing a deep research, put the research doc under ./docs/research. You shall look into that directory before doing researches.
- Automation via Makefile:
- Explore existing Makefile targets and use them accordingly
- For new automation tasks, always add a Makefile target instead of creating shell scripts
- Keep automation consistent and discoverable
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 · 214 lines · 5,226 tokens per session scan A d94de0399865
rust-lib-template CLAUDE.md is an instructions file published in the GitHub repository tyrchen/rust-lib-template (51 stars, last pushed 3mo ago), licensed MIT. It adds 5,226 tokens to every session, about $0.0261 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to rust-lib-template AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
cli AGENTS.md
Instructions for googleworkspace/cli, covering agents.md, project overview, build & test, changesets and architecture.
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
ton-rs AGENTS.md
Instructions for ston-fi/ton-rs, covering ton-rs agent guide, repository, boundaries, public api and ton invariants.
cli AGENTS.md
Instructions for rustfs/cli, covering agents.md - ai development guidelines, language requirements, first-principles reasoning, workflow and 0. branch base policy.