Borrowing it
Nothing to install: this file belongs to Muvon/octobrain. 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/Muvon/octobrain/master/AGENTS.mdgit clone --depth 1 https://github.com/Muvon/octobrainWrote 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/muvon/octobrain/agents-md)<a href="https://agentmods.dev/instructions/muvon/octobrain/agents-md"><img src="https://agentmods.dev/badge/instructions/muvon/octobrain/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/muvon/octobrain/agents-md"><img src="https://agentmods.dev/badge/instructions/muvon/octobrain/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 | $0.02898 | $0.02898 |
| Opus 5.5 | $0.01159 | $0.01159 |
| Sonnet 5.5 | $0.00580 | $0.00580 |
| Haiku 4.5 | $0.00290 | $0.00290 |
Grade A, and why
octobrain 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 8d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Octobrain — AGENTS.md
Standalone memory management system for AI context and conversation state: a CLI (octobrain) plus an MCP server, in Rust (MSRV 1.95, edition 2021). LanceDB vector storage, rmcp for MCP, octolib for embeddings/reranking. Apache-2.0, Muvon Un Limited.
Commands
Two build modes, both must stay green: fast loop --no-default-features (no heavy local models; what Makefile targets use) and full gate --all-features (what CI + pre-commit run; also compiles beir_bench; needs protoc on PATH).
- Dev build:
cargo build --no-default-features· Release:cargo build --no-default-features --release - Check:
cargo check --no-default-features --all-targets· All feature combos:make check-features - Format (write):
cargo fmt --all· Format (verify):cargo fmt --all -- --check—make fmtis verify-only - Lint:
cargo clippy --no-default-features --all-targets -- -D warnings(CI/pre-commit variant uses--all-features) - Tests light:
cargo test --no-default-features· CI parity:cargo test --all-features· One test:cargo test --no-default-features <test_name> - Coverage:
cargo llvm-cov --summary-only --all-features --ignore-filename-regex '_tests\.rs$' - Run CLI:
cargo run --no-default-features -- <subcommand>· MCP server:cargo run --no-default-features -- mcp(stdio) or-- mcp --bind=host:port(streamable HTTP) - BEIR retrieval bench (local, free):
bash benches/scripts/run_retrieval.shorcargo run --release --features bench --bin beir_bench -- <dataset_dir> [label] - Completions:
make install-completions/make test-completions make cireferences nonexistent targets (format-check,lint) — run the four commands above instead
Where to look
| Task | Start here |
|---|---|
| Memory CLI command | src/cli.rs (MemoryCommand) → src/commands.rs (execute_memory_command) |
| Knowledge / box CLI command | src/cli.rs (KnowledgeCommand, BoxCommand) → src/commands.rs |
| MCP tool | src/mcp/server.rs (#[tool] macro + Params struct) → src/mcp/memory.rs / src/mcp/knowledge.rs provider |
| Config option | src/config.rs struct + config-templates/default.toml — always both, same commit |
| Memory data model | src/memory/types.rs (incl. MemoryType, relationship enums) → src/memory/store.rs (schema, batch_to_memories) |
| Knowledge data model | src/knowledge/types.rs → src/knowledge/store.rs |
| Search internals | src/memory/store.rs: search_memories / hybrid_search / expand_query_embedding |
| Consolidation | src/memory/manager.rs: consolidate_goal, sleep_consolidate |
| Reranking | src/memory/reranker_integration.rs + RerankerConfig in src/config.rs |
| Cross-process embedding sharing | src/embedding.rs + src/embedding/shared.rs (election, loopback attach) |
| Knowledge boxes | src/knowledge/boxes.rs (registry/git/scope) → src/knowledge/manager.rs (import_box / sync_boxes) |
| Storage paths | src/storage.rs · LanceDB index tuning: src/vector_optimizer.rs |
| CLI output | src/memory/formatting.rs (memory), src/knowledge/formatting.rs (knowledge) |
| Benchmarks | benches/README.md — BEIR is local/metric-only; LongMemEval is Docker + .env + paid LLM calls |
| Recent changes | CHANGELOG.md |
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.
- 8d ago Changed · +111 tokens per session ee6b58c27837
- 1mo ago Changed · -167 lines · -1,754 tokens per session b07e001d65a0
- 1mo ago First seen · 270 lines · 4,541 tokens per session scan A 1d52c642ed48
octobrain AGENTS.md is an instructions file published in the GitHub repository Muvon/octobrain (15 stars, last pushed 6d ago), licensed Apache-2.0. It adds 2,898 tokens to every session, about $0.0116 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 2026-09-17.
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).
next.js AGENTS.md
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, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.