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/cofy-x/axern/agents-mdgit clone --depth 1 https://github.com/cofy-x/axernWrote 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/cofy-x/axern/agents-md)<a href="https://agentmods.dev/instructions/cofy-x/axern/agents-md"><img src="https://agentmods.dev/badge/instructions/cofy-x/axern/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 | $0.00925 | $0.00925 |
| Opus 5 | $0.00463 | $0.00463 |
| Sonnet 5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
axern 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 4d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Axern Agent Contract
Scope
This file defines repository-wide rules for axern. Apply it to every task,
then read the nearest subtree AGENTS.md before changing code there. A local
contract may add stricter rules but cannot override this file.
Minimum Context
Read only the context required for the task:
- Use the Module Guide to find the owning subtree. Read
its
AGENTS.mdwhen present and itsREADME.md. - Read Project Overview for root layout, workspace, build orchestration, or placement changes.
- Read Runtime Stack only when behavior crosses service, SDK, storage, runtime, gateway, or network boundaries.
- Read Coding Standards for language rules and the validation baseline.
- Use the Documentation Guide to find product direction, architecture, verification, and operational material.
Do not read every repository document by default. Subsystem-local work should normally need this file plus the local contract and README.
Sources Of Truth
When documentation disagrees with executable configuration or code, verify the behavior and fix the stale document in the same change.
| Concern | Source of truth |
|---|---|
| Workspace membership | go.work, Cargo.toml, pnpm-workspace.yaml, pyproject.toml |
| Root commands | Makefile, mk/*.mk, make help |
| Public and internal RPC shapes | sdk/proto and generated-code checks |
| Subsystem ownership and validation | nearest AGENTS.md; owning README.md when no local contract exists |
| User and operator workflows | owning README.md or docs/operations/ runbook |
| Cross-subsystem runtime boundaries | .x/runtime-stack.md |
| Long-term product direction | docs/product/product-direction.md |
Repository Constraints
apps/contains executable product entrypoints.control/,gateway/,runtime/, andnetwork/contain platform services and data planes owned by those areas.sdk/contains public language SDKs and protobuf contracts; it does not contain product applications.lib/contains repository-internal libraries shared by multiple Axern modules. Do not move single-module helpers there.- Keep Go, Rust, TypeScript, and Python as first-class workspaces. Add a workspace member only when it has a concrete owner and update its workspace configuration and relevant docs together.
- Do not reintroduce template frontend, dashboard, Tauri, or unrelated demo applications without an explicit product requirement.
- Keep root deployment commands and
deploy/helm/cloud-neutral. Provider- specific values, credentials, cluster paths, and cloud resource orchestration belong in an external workspace or provider repository.
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.
- 4d ago First seen · 88 lines · 925 tokens per session scan A 4a1799c47977
axern AGENTS.md is an instructions file published in the GitHub repository cofy-x/axern (59 stars, last pushed today), licensed Apache-2.0. It adds 925 tokens to every session, about $0.0046 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 2026-08-30.
Other instructions, from other repositories
sandboxd AGENTS.md
AGENTS.md instructions for tastyeffectco/sandboxd, covering agents.md — operating sandboxd, what this is, prerequisites, install and core api.
tensorlake AGENTS.md
AGENTS.md instructions for tensorlakeai/tensorlake, a project described as: Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications.
mitos CLAUDE.md
Instructions for mitos-run/mitos, covering claude.md, project overview, operating principles, commands and architecture.
tensorlake CLAUDE.md
Claude Code instructions for tensorlakeai/tensorlake, covering claude.md, project overview, common commands, install dependencies and build and format code (black + isort).
sprites-ex CLAUDE.md
Claude Code instructions for superfly/sprites-ex, covering sprites elixir sdk, quick reference, common commands, install dependencies and compile.
agent-box AGENTS.md
Instructions for 0xferrous/agent-box, covering pre commit, image, returns: /nix/store/ -source, wrappers and portal adr.