Borrowing it
Nothing to install: this file belongs to Muvon/octofs. 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/octofs/master/AGENTS.mdgit clone --depth 1 https://github.com/Muvon/octofsWrote 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/octofs/agents-md)<a href="https://agentmods.dev/instructions/muvon/octofs/agents-md"><img src="https://agentmods.dev/badge/instructions/muvon/octofs/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/octofs/agents-md"><img src="https://agentmods.dev/badge/instructions/muvon/octofs/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 | $0.01613 | $0.01613 |
| Opus 5.5 | $0.00645 | $0.00645 |
| Sonnet 5.5 | $0.00323 | $0.00323 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
octofs 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 5d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Octofs — AGENTS.md
Standalone Rust binary exposing filesystem tools (view, text_editor, batch_edit, extract_lines, shell, workdir) over MCP — stdio or streamable HTTP — with native SSH/SFTP remote file support. Rust 1.95+ · rmcp 3.x · tokio · axum.
Commands
- Build:
cargo build· Release:cargo build --release· Dev run:cargo run -- mcp(stdio; add--bind 127.0.0.1:12345for HTTP;RUST_LOG=debugfor logs) - Format:
cargo fmt· Lint:cargo clippy --all-features -- -D warnings· Test:cargo test --all-features(one suite:cargo test --all-features <name>) - Coverage:
make coverage(needs cargo-llvm-cov + llvm-tools-preview; excludes*_tests.rs) - This checkout auto-syncs to the dev server — run build/test/clippy there (
ssh dev), not on this machine.
Where to look
| Task | Start here |
|---|---|
| Add / change an MCP tool | .agents/tool-authoring.md, then src/mcp/server.rs (Params + #[tool]) → src/mcp/fs/*.rs (execute fn) → src/mcp/fs/mod.rs (re-export) → tests |
| Tool schemas & model-facing descriptions | src/mcp/server.rs — Params structs and #[tool(...)] blocks |
| view / create / undo / path resolution | src/mcp/fs/core.rs + src/mcp/fs/file_ops.rs |
| str_replace / batch_edit internals / file locking | src/mcp/fs/text_editing.rs |
| Directory listing, glob + content filtering | src/mcp/fs/directory.rs + src/mcp/fs/search.rs |
| Delta views / view cache | src/mcp/fs/delta.rs — note_write, note_create, render_whole_file |
| Background jobs / MCP resources / subscriptions | src/mcp/fs/background.rs + handlers in src/mcp/server.rs |
| SSH/SFTP paths, auth, connection pool | src/mcp/fs/remote.rs — read .agents/remote-ssh.md first |
Line ids (N:hh) / stale-id verification |
src/utils/line_hash.rs |
| Truncation / token budgets | src/utils/truncation.rs |
| Hints appended to tool responses | src/mcp/request_ctx.rs (push_hint → append_hints) |
| Startup, transports, shutdown cleanup | src/main.rs, src/cli.rs; HTTP access control in src/http_auth.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.
- 5d ago Changed · +1 lines · +80 tokens per session 5bd7d69d1ad2
- 1mo ago Changed · +43 tokens per session 60f96c3186ff
- 1mo ago Changed · -113 lines · -1,339 tokens per session a8fd9f83ebfd
- 2mo ago First seen · 175 lines · 2,829 tokens per session scan A 5165f6d9f90b
octofs AGENTS.md is an instructions file published in the GitHub repository Muvon/octofs (18 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,613 tokens to every session, about $0.0065 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.
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.