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/agentworkforce/burn/agents-mdgit clone --depth 1 https://github.com/AgentWorkforce/burnWhat 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 | $0.01449 | $0.01449 |
| Opus 5 | $0.00724 | $0.00724 |
| Sonnet 5 | $0.00290 | $0.00290 |
| Haiku 4.5 | $0.00145 | $0.00145 |
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 yesterday.
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 — 138 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,ledger,analyze,ingest}/ are internal modules.
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.
- yesterday 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 (5 stars, last pushed 8d ago), licensed Apache-2.0. It adds 1,449 tokens to every session, about $0.0072 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.