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/vieko/bonfire/agents-mdgit clone --depth 1 https://github.com/vieko/bonfireWhat 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 | $0.01250 | $0.01250 |
| Opus 5 | $0.00625 | $0.00625 |
| Sonnet 5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
bonfire 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working with this repository.
What this repo is
Bonfire — a file convention + per-host adapters for cross-session AI coding memory.
bonfire/
├── pi/ # Pi adapter package (TypeScript, jiti runtime)
│ ├── extension.ts # hooks session_compact + session_shutdown
│ ├── lib.ts # pure functions (extraction, rendering, fence ops)
│ ├── test.mjs # unit tests
│ └── smoke.mjs # composition + file-IO smoke test
├── claude/ # Claude Code Stop hook (plain ESM JS, no deps)
│ ├── lib.mjs # shared fence-contract primitives (importable)
│ ├── update-bonfire.mjs
│ └── test.mjs # unit + integration tests
├── skills/bonfire/ # Cross-agent fallback skill
│ ├── SKILL.md # disable-model-invocation: true
│ ├── commands/end.md # outcome-oriented spec
│ └── templates/index.md
├── conformance.mjs # cross-producer fence-contract harness
├── README.md
├── CHANGELOG.md
└── AGENTS.md # this file
Key invariants
- Fence format is the contract:
<!-- bonfire:auto-inflight:start v1 -->and<!-- bonfire:auto-sessions:start v1 -->. Both adapters must produce identical fence shapes; the fallback skill must too. Bump thev1suffix only with a coordinated migration.conformance.mjsenforces byte-identity — see the sync contract below. - Opt-in gate: presence of
<git-root>/.bonfire/directory. Adapters never auto-create it. The opt-in is consciously per-repo. - Short session id: ≥8 random hex chars, skipping UUIDv7 timestamp prefixes. Both adapters use
slice(8, 16)of the hyphen-stripped UUID. - Cap: 5 newest rows in the sessions fence. Older rows drop.
- De-dupe by
[<host>:<short-id>]: same session updates its row instead of duplicating. - Garbage + stale detection: in-flight from a different session, or matching
/no conversation (content|messages?)/i, gets overwritten.
Fence-contract sync contract
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 · 89 lines · 1,250 tokens per session scan A 64c867efaf57
bonfire AGENTS.md is an instructions file published in the GitHub repository vieko/bonfire (10 stars, last pushed 9d ago), licensed MIT. It adds 1,250 tokens to every session, about $0.0063 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
vscode buildNext.instructions.md
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).
spec-kit AGENTS.md
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.
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.
langchain AGENTS.md
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.
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).
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.