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/copilot-instructionsgit 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/copilot-instructions)<a href="https://agentmods.dev/instructions/jyunming/axon/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/jyunming/axon/copilot-instructions.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 | $0.04209 | $0.04209 |
| Opus 5 | $0.02105 | $0.02105 |
| Sonnet 5 | $0.00842 | $0.00842 |
| Haiku 4.5 | $0.00421 | $0.00421 |
Grade A, and why
Axon copilot-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 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 — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Axon Knowledge Center — Copilot Instructions
These instructions give GitHub Copilot persistent context about the Axon knowledge center so you can ingest and retrieve information correctly across every session.
What Axon Is
Axon is a local RAG (Retrieval-Augmented Generation) system exposed as a
REST API (localhost:8420) and as an MCP stdio server. It stores embeddings
in a local vector store (ChromaDB by default) and a BM25 index. All storage
is free and local; only the LLM call (if using Ollama) runs locally too.
Project Namespaces
Projects group related knowledge. The active project determines which vector store collection and BM25 index are read and written.
| Project name | Use for |
|---|---|
default |
General-purpose knowledge, catch-all (canonical name; was _default in earlier versions) |
| (add project-specific rows here as namespaces are created) |
Switch the active project with POST /project/switch before ingesting if the
content belongs to a specific namespace.
Hierarchical projects (up to 5 levels)
Projects support slash-separated nesting up to 5 levels deep:
research/ ← top-level parent
research/papers/ ← child
research/papers/2024 ← grandchild
research/papers/2024/q1 ← great-grandchild (max depth: 5 segments total)
Searching a parent automatically searches all its descendants. When you
switch_project("research"), Axon builds a MultiVectorStore and
MultiBM25Retriever that fan out queries across research, research/papers,
and research/papers/2024 — results are merged and ranked together.
Writes (ingestion) always go to the parent's own store. Reads fan out.
Pattern for searching across unrelated topics: If you need to search both
react-docs and python-stdlib together, place them under a shared parent:
docs/react-docs and docs/python-stdlib. Then switch_project("docs")
searches both in one call.
Use list_projects to discover available namespaces before switching.
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 · 417 lines · 4,209 tokens per session scan A 2cc9f821edb0
Axon copilot-instructions.md is an instructions file published in the GitHub repository jyunming/Axon (4 stars, last pushed 4d ago), licensed MIT. It adds 4,209 tokens to every session, about $0.0210 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
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.