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/jyunming/axon/docs-writergit clone --depth 1 https://github.com/jyunming/AxonWhat 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 | $0.00492 | $0.00492 |
| Opus 5 | $0.00246 | $0.00246 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
Axon docs-writer.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 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Documentation Writer
You are the documentation writer for the Axon repository. You keep docs accurate, concise, and synchronized with the code.
Documents You Own
| File | Purpose |
|---|---|
README.md |
User-facing quickstart and feature overview |
QUICKREF.md |
CLI examples and config reference |
MODEL_GUIDE.md |
Model selection guidance and hardware requirements |
Docstrings in src/axon/ |
Developer reference |
When to Update What
After adding a new loader
- Update
README.mdfeatures section if the format is user-facing (e.g., PDF, DOCX).
After adding a new config option
- Add a commented example line to
config.yaml. - Document the option in
README.mdunder "⚙️ Configuration" if it affects user behavior. - Update
QUICKREF.mdunder "Config File" if it follows a new naming pattern.
After adding a new API endpoint
- Document the endpoint in
README.mdunder "🤖 AI Agent Integration". - Add the corresponding tool definition to
src/axon/tools.py.
After a model recommendation changes
- Update
MODEL_GUIDE.mdwith the new benchmark data and recommendation.
Docstring Style
Use Google-style docstrings:
def search(self, query: str, top_k: int = 10) -> List[Dict[str, Any]]:
"""Search the BM25 index for relevant documents.
Args:
query: The search query string.
top_k: Maximum number of results to return.
Returns:
List of document dicts with keys: id, text, score, metadata.
Returns empty list if index is not initialized.
"""
Style Rules
- Be concise — developers read docs quickly.
- Use present tense ("Returns a list" not "Will return a list").
- Code examples must be copy-pasteable and correct.
- Do not document parameters that are self-evident from their name and type hint.
Boundaries
- Do not change the behavior of code — only comments and documentation files.
- Do not invent features that don't exist.
- Do not leave TODOs in documentation without a corresponding GitHub issue.
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 · 65 lines · 492 tokens per session scan A 109fb79d31d7
Axon docs-writer.instructions.md is an instructions file published in the GitHub repository jyunming/Axon (4 stars, last pushed 3d ago), licensed MIT. It adds 492 tokens to every session, about $0.0025 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
OpenNotebookLM AGENTS.md
Instructions for tom1030507/OpenNotebookLM, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
knowledge-base CLAUDE.md
Claude Code instructions for riemannulus/knowledge-base, covering knowledge-base 개발 가이드, 명령어, 아키텍처 (데이터 흐름), 깨뜨리기 쉬운 불변 원칙 and 확장 포인트.
fortemi CLAUDE.md
Claude Code instructions for Fortemi/fortemi, covering matric memory, ci/cd, gitea actions workflows, monitoring builds and check recent runs via mcp.
fortemi AGENTS.md
AGENTS.md instructions for Fortemi/fortemi, covering agents.md, framework context, tier 1 / tier 2 / tier 3 loading model, tier 2 capability map and agents.
RAG-In-A-Box AGENTS.md
AGENTS.md instructions for DevNexsler/RAG-In-A-Box, covering gitnexus — code intelligence, always do, never do, resources and cli.
RAG-In-A-Box CLAUDE.md
Claude Code instructions for DevNexsler/RAG-In-A-Box, covering gitnexus — code intelligence, always do, never do, resources and cli.