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/statespace-tech/statespace/agents-mdgit clone --depth 1 https://github.com/statespace-tech/statespaceWhat 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 | $0.02486 | $0.02486 |
| Opus 5 | $0.01243 | $0.01243 |
| Sonnet 5 | $0.00497 | $0.00497 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
statespace AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Statespace
Overview
Statespace is an open-source AI runtime/framework. This monorepo contains the Rust implementation.
Build/Test Commands
- Build:
cargo build - Test:
cargo test - Lint:
cargo clippy --all-targets -- -D warnings - Format:
cargo fmt --all - Check:
cargo check
Pre-commit Hooks
Pre-commit hooks run cargo fmt --check and cargo clippy. To enable:
git config core.hooksPath .githooks
Note: On macOS, the linker needs to find libiconv (pulled in by reqwest/rustls). The .envrc handles this automatically with direnv. Without direnv, set:
export LIBRARY_PATH="$(xcrun --show-sdk-path)/usr/lib${LIBRARY_PATH:+:$LIBRARY_PATH}"
Project Structure
statespace/
├── Cargo.toml # Workspace manifest
├── binaries/
│ └── statespace-cli/ # CLI binary
│ └── src/
│ ├── main.rs
│ ├── args.rs
│ ├── config.rs
│ ├── error.rs
│ ├── commands/
│ └── gateway/
├── crates/
│ ├── statespace-tool-runtime/ # Core runtime library (no HTTP, no CLI)
│ │ └── src/
│ │ ├── lib.rs
│ │ ├── error.rs
│ │ ├── executor.rs
│ │ ├── frontmatter.rs
│ │ ├── protocol.rs
│ │ ├── security.rs
│ │ ├── spec.rs
│ │ ├── tools.rs
│ │ └── validation.rs
│ ├── statespace-server/ # HTTP server library
│ │ └── src/
│ │ ├── lib.rs
│ │ ├── content.rs
│ │ ├── error.rs
│ │ ├── semantics.rs
│ │ └── server.rs
│ └── statespace-templates/ # Embedded init templates and starters
│ ├── build.rs
│ └── src/
│ ├── lib.rs
│ ├── AGENTS.md # Written to new projects — guides coding agents building/iterating on the app
│ ├── llms.txt # Written to new projects — served at GET / of deployed apps; describes the HTTP API contract to consuming agents
│ ├── .gitignore
│ └── starters/ # Per-database starter projects
└── docs/
└── design/ # RFDs
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.
- 2d ago First seen · 240 lines · 2,486 tokens per session scan A df1dcc6df276
statespace AGENTS.md is an instructions file published in the GitHub repository statespace-tech/statespace (871 stars, last pushed 27d ago), licensed MIT. It adds 2,486 tokens to every session, about $0.0124 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
ai-doc-gen AGENTS.md
Instructions for divar-ir/ai-doc-gen, covering ai documentation generator, build & test, install dependencies (python 3.13 required, <3.14), run analysis (writes .ai/docs/.md) and generate readme.
ai-doc-gen CLAUDE.md
Instructions for divar-ir/ai-doc-gen: See AGENTS.md for project instructions (commands, architecture, conventions, gotchas).
mcp-agent-langchainjs AGENTS.md
Instructions for Azure-Samples/mcp-agent-langchainjs, covering mcp agent langchain.js project instructions, architecture overview, component communication flow, key architectural patterns and authentication & state management.
pruna-skills AGENTS.md
Instructions for PrunaAI/pruna-skills, covering pruna skills (agent notes), how it works, clarification (library-wide), install and layout.
backend.ai AGENTS.md
AGENTS.md instructions for lablup/backend.ai, covering ai coding agent guidelines, document structure (agents.md / knowledge.md), writing style, document index and absolute rules (global).
mcp-agent-langchainjs api.instructions.md
Instructions for Azure-Samples/mcp-agent-langchainjs: If you get it right you'll get a 1000$ bonus, but if you get it wrong you'll be fired.