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/agents-mdgit clone --depth 1 https://github.com/jyunming/AxonWrote 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/jyunming/axon/agents-md)<a href="https://agentmods.dev/instructions/jyunming/axon/agents-md"><img src="https://agentmods.dev/badge/instructions/jyunming/axon/agents-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 | $0.00620 | $0.00620 |
| Opus 5 | $0.00310 | $0.00310 |
| Sonnet 5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
Axon AGENTS.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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Core code lives in src/axon/. Key areas: api_routes/ for FastAPI handlers, graph_backends/ and dynamic_graph/ for graph retrieval, code_graph.py and code_retrieval.py for code-aware RAG, and repl.py / cli.py / mcp_server.py for user-facing entry points. Tests live in tests/; VS Code extension end-to-end coverage is under tests/e2e/. The bundled extension is in integrations/vscode-axon/. Top-level docs are in docs/.
Build, Test, and Development Commands
pip install -e ".[dev]": install Axon with local dev tools.make format: runblackandruff --fixonsrc/andtests/.make lint: runruff checkandblack --check.make type-check: runmypy src/axon/ --ignore-missing-imports.make test: run the Python test suite.pytest tests/test_api.py -v --no-cov: run a focused test file.pytest -q tests/e2e: run end-to-end coverage; requires Node and the compiled VS Code extension.axon,axon-api,axon-ui,axon-mcp: run the REPL, API server, Streamlit UI, and MCP server.
Coding Style & Naming Conventions
Use Python 3.10+ and 4-space indentation. Black and Ruff are the enforced style tools; line length is 100. Prefer type hints on public functions and keep module names snake_case. Use PascalCase for classes, snake_case for functions/tests, and descriptive test names such as test_ingest_blocks_windows_system_path.
Testing Guidelines
Pytest is the main framework. Put new tests in tests/ as test_*.py; keep one behavior per test where practical. Add regression tests for bug fixes. For surface changes, cover the narrowest layer first (unit/API/REPL) before broader e2e tests. Avoid writing to real user config or store paths; use temp directories and explicit config overrides.
Commit & Pull Request Guidelines
Recent history favors short, imperative subjects with optional scopes, for example fix(cli): add --non-interactive flag or api(query): harden dry-run. Keep commits focused. PRs should include: the behavior change, test coverage, linked issues when applicable, and screenshots/GIFs for UI or VS Code panel changes. Update docs when commands, config, APIs, or user-visible flows change.
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 · 27 lines · 620 tokens per session scan A 8b61ecb4043c
Axon AGENTS.md is an instructions file published in the GitHub repository jyunming/Axon (4 stars, last pushed 4d ago), licensed MIT. It adds 620 tokens to every session, about $0.0031 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.