Borrowing it
Nothing to install: this file belongs to Muvon/octomind. 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/octomind/master/AGENTS.mdgit clone --depth 1 https://github.com/Muvon/octomindWrote 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/octomind/agents-md)<a href="https://agentmods.dev/instructions/muvon/octomind/agents-md"><img src="https://agentmods.dev/badge/instructions/muvon/octomind/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/octomind/agents-md"><img src="https://agentmods.dev/badge/instructions/muvon/octomind/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 | $0.04151 | $0.04151 |
| Opus 5.5 | $0.01660 | $0.01660 |
| Sonnet 5.5 | $0.00830 | $0.00830 |
| Haiku 4.5 | $0.00415 | $0.00415 |
Grade A, and why
octomind 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 9d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Octomind — AGENTS.md
Open-source AI coding agent and agent runtime: one Rust binary, any model (multi-provider via octolib), MCP-native. Sessions run interactively (CLI), non-interactively (--format), or as daemons (ACP stdio / WebSocket). TOML config is the single source of truth — model, tools, roles, compression, supervisor and learning all derive from it. Rust 1.95+ (MSRV enforced), tokio async, clap CLI.
Commands
- Setup:
cargo build· Hooks:pip install pre-commit && pre-commit install(fmt + clippy + check run on every commit) - Dev:
cargo run· Build:cargo build/cargo build --release(make build) - One-shot gate:
make dev(fmt + clippy + test) - Fmt:
cargo fmt --all· Check-only:make fmt-check - Lint:
cargo clippy --all-targets --all-features -- -D warnings - Test:
cargo test(debug build — what CI runs;make test=cargo test --release, slower first run) - Coverage:
make coverage—cargo llvm-covwith*_tests.rsexcluded so percentages describe product code - Cross-compile/dist:
make build-all/make dist(usescross, seeCross.toml) · Release packaging:build.sh - Bench (token-efficiency vs committed baseline): protocol in
bench/README.md - Build/test environment prereqs are per-OS — see Platforms below
Where to look
| Task | Start here |
|---|---|
| Add an MCP tool | schema in that server's get_all_functions() — src/mcp/core/functions.rs, src/mcp/orchestration/mod.rs, src/mcp/runtime/mod.rs, src/mcp/agent/functions.rs → implement in same module → match arm in src/mcp/mod.rs route_builtin_tool() → register in src/mcp/tool_map.rs |
Add a session command (/foo) |
src/session/chat/session/commands/<name>.rs returning CommandResult → mod + routing arm in commands/mod.rs process_command() → new CommandOutput variant if the result shape is new → constant + row in the fixed-size BUILTIN_COMMANDS array in src/session/chat/commands.rs (bump the length; Reach::CliOnly hides it from WebSocket clients) |
| Change a config field/default | config-templates/default.toml FIRST, then the matching type in src/config/ |
| Config load / merge / role resolution | src/config/loading.rs (load()), src/config/merge.rs (get_merged_config_for_role()) |
| Tool not found / routing bugs | src/mcp/tool_map.rs get_server_for_tool() → src/mcp/mod.rs try_execute_tool_call() |
| Session-scoped state | src/session/context.rs init_session_services() — task-local SessionId via with_session_id |
| Session main loop | src/session/chat/session/main_loop.rs (init_session_runtime()) |
| Response / tool execution | src/session/chat/response.rs, response/tool_execution.rs, response/tool_result_processor.rs |
| Skill auto-activation / validators | src/mcp/runtime/skill_auto.rs (run_activation, run_validators) |
| Compression | src/session/chat/conversation_compression/ (decision.rs, apply.rs, schema.rs, attention/) |
| Supervisor (gate, plan, detect, condense, resolve, authorizer, stats) | src/supervisor/ |
| Learning (extract / inject / retention / file backend / evolution) | src/supervisor/learning/ |
| Workflows | src/workflow/ (schema.rs, run.rs, validate.rs) + templates config-templates/workflow*.toml |
| Taps (shareable project agents) | src/agent/ (registry, taps, resolver, deps) |
| Layers / guardrails / pipes | src/session/layers/, src/session/guardrails.rs, src/session/pipe.rs |
| ACP / WebSocket servers | src/acp/agent.rs, src/websocket/server.rs |
| MCP elicitation (who answers, routing, timers) | src/mcp/elicitation.rs (answerers, pending questions), src/mcp/client.rs (IN_FLIGHT_CALLS, calls_awaiting_elicitation, create_elicitation), terminal prompt src/session/chat/elicitation.rs |
| Sandbox / embeddings / telemetry | src/sandbox/, src/embeddings/, src/telemetry.rs |
| CLI subcommands | src/commands/ (run, tap, untap, workflow, config, send, server, acp, …) |
| Path / directory constants | src/directories.rs |
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.
- 9d ago Changed · +1 lines · +87 tokens per session a3a326efb14e
- 11d ago Changed · +3 lines · +242 tokens per session 51ac146ddaf2
- 1mo ago Changed · +38 tokens per session 5216870ca53c
- 1mo ago Changed · +1 lines · +30 tokens per session 3c5bfb8882df
- 1mo ago Changed · -176 lines · -219 tokens per session 021300ec1cb5
- 2mo ago Changed · +43 tokens per session 2f6dab9e0756
- 2mo ago First seen · 318 lines · 3,930 tokens per session scan A a8b451db8c40
octomind AGENTS.md is an instructions file published in the GitHub repository Muvon/octomind (563 stars, last pushed yesterday), licensed Apache-2.0. It adds 4,151 tokens to every session, about $0.0166 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 2026-08-30.
octomind AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| octomind AGENTS.mdMuvon/octomind | Instructions file | 563 | yesterday | Apache-2.0 | A | 4,151 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |