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/immunefomo/fetchira/claude-mdgit clone --depth 1 https://github.com/ImmuneFOMO/fetchiraWhat 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 | $0.01321 | $0.01321 |
| Opus 5 | $0.00660 | $0.00660 |
| Sonnet 5 | $0.00264 | $0.00264 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade A, and why
fetchira 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Messages
Use Conventional Commits with short subject line only. No body, no footers, no explanations. Good examples:
fix(wallet): refresh JWT after setup completesfeat(wallet): cut over to type-3 deposit wallet contractrefactor(commands): simplify error mapping for depositschore(tauri): update capability for filesystem access
Never write long commit bodies or "This change does X because...".
Core Philosophy — Write Code That Looks Human
- Match existing code 1:1 — Before touching any file, read the surrounding functions and module. Copy naming, style, error patterns, and level of abstraction exactly. Do not "improve" the local style.
- Minimal viable solution — Solve the task with the smallest amount of code possible. No extra abstractions, traits, newtypes, builder patterns, or "future-proofing" unless there is a clear, immediate reduction in duplication or readability win in this exact context.
- Avoid churny refactors — Never introduce a one-use temporary variable just to name it before passing it on. Keep the expression inline unless the name carries real domain meaning or eliminates real duplication.
- Be slightly lazy where it makes sense — If the surrounding code is concise and works, match it. Don't add ceremony that isn't already present.
- Comments:
- Never comment what the code does (code should be self-documenting).
- Only comment why — a non-obvious business reason, important trade-off, or invariant the type system doesn't enforce.
- No emojis. No corporate fluff ("leverage", "utilize", "robustly", "seamlessly", "best practice", etc.).
- After writing code — Re-read the changed functions. Remove any defensive checks, clones, or unwraps that are now guaranteed safe by the caller or surrounding invariants.
- Naming — Use the short, domain-specific names already established in the project (e.g.
tx,addr,bal,wallet). Never default to generic names likedata,result,item,processed,response,value,obj,entity, etc.
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 · 81 lines · 1,321 tokens per session scan A cae7c9d569cd
fetchira CLAUDE.md is an instructions file published in the GitHub repository ImmuneFOMO/fetchira (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,321 tokens to every session, about $0.0066 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
skills AGENTS.md
Instructions for qdrant/skills, covering qdrant skills, project overview, project structure, navigating skills locally and conventions.
agentic-playwright selectors.instructions.md
Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.
nezha AGENTS.md
AGENTS.md instructions for hanshuaikang/nezha, covering nezha — agents.md, 项目概述, 开发命令, 架构设计 and 前端(src/).
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
llm-ide-rules pytest-integration-tests.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering pytest integration tests and example integration test.
toki AGENTS.md
Instructions for choi138/toki, covering workspace rules, source of truth, toki workflow, required checks and global safety rules.