Borrowing it
Nothing to install: this file belongs to AgentWorkforce/burn. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AgentWorkforce/burn/main/AGENTS.mdgit clone --depth 1 https://github.com/AgentWorkforce/burnWrote 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/agentworkforce/burn/agents-md)<a href="https://agentmods.dev/instructions/agentworkforce/burn/agents-md"><img src="https://agentmods.dev/badge/instructions/agentworkforce/burn/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/agentworkforce/burn/agents-md"><img src="https://agentmods.dev/badge/instructions/agentworkforce/burn/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01946 | $0.01946 |
| Opus 5.5 | $0.00778 | $0.00778 |
| Sonnet 5.5 | $0.00389 | $0.00389 |
| Haiku 4.5 | $0.00195 | $0.00195 |
Grade A, and why
burn 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 18d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide for relayburn
Conventions an agent (or human) needs to know to work productively in this repo.
Pairs with README.md — README is what burn does, this file is
how to work on it.
Layout
The repo is Rust-first. crates/ is the source of truth.
Rust crates (crates/)
Only relayburn-sdk and relayburn-cli are published to crates.io. Crate
names are prefixed relayburn-* because burn is taken on crates.io; the
binary keeps the burn invocation via [[bin]] name = "burn" in
relayburn-cli.
relayburn-sdk — PUBLISHED to crates.io; embedding API.
src/{reader,source,ledger,analyze,ingest}/ are internal
modules: reader/ is burn's record model (types,
classifier, inference, span trees), source/ maps
relayhistory evidence onto it, ingest/ keeps the
ledger up to date from the relayhistory store.
The public verb surface lives in
src/{query_verbs,export_verbs,ingest_verb}.rs.
relayburn-cli — PUBLISHED to crates.io; produces the `burn` binary.
Consumes the SDK as an external embedder would.
relayburn-sdk-node — napi-rs bindings; built in CI to produce
@relayburn/sdk .node artifacts. Not published to crates.io.
Build order is relayburn-sdk -> relayburn-cli, with relayburn-sdk-node also
depending on relayburn-sdk. Toolchain is pinned in rust-toolchain.toml at
the repo root.
Every new read verb should land first in relayburn-sdk as a pure function or
LedgerHandle method. The CLI and MCP presenter surfaces should wrap SDK calls
rather than duplicating query logic.
npm packages (packages/)
The npm workspace contains wrappers and platform package manifests only:
packages/sdk-node — @relayburn/sdk Node facade over relayburn-sdk-node.
packages/sdk-node/npm/* — @relayburn/sdk-<platform> prebuilt native packages.
packages/mcp — @relayburn/mcp stdio MCP presenter over @relayburn/sdk.
packages/relayburn — unscoped npm install wrapper exposing `burn`.
packages/relayburn/npm/* — @relayburn/cli-<platform> prebuilt binary packages.
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.
- 18d ago Changed 04d0c4b0fd54
- 25d ago Changed · +18 lines · +255 tokens per session bebda94425c1
- 1mo ago Changed · +23 lines · +242 tokens per session 57c7ca9cccb5
- 2mo ago First seen · 138 lines · 1,449 tokens per session scan A 8cfc4607d536
burn AGENTS.md is an instructions file published in the GitHub repository AgentWorkforce/burn (8 stars, last pushed today), licensed Apache-2.0. It adds 1,946 tokens to every session, about $0.0078 per session on Opus 5.5. 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.
burn AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| burn AGENTS.mdAgentWorkforce/burn | Instructions file | 8 | today | Apache-2.0 | A | 1,946 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |