Borrowing it
Nothing to install: this file belongs to statespace-tech/statespace. 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/statespace-tech/statespace/main/AGENTS.mdgit clone --depth 1 https://github.com/statespace-tech/statespaceWrote 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/statespace-tech/statespace/agents-md)<a href="https://agentmods.dev/instructions/statespace-tech/statespace/agents-md"><img src="https://agentmods.dev/badge/instructions/statespace-tech/statespace/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/statespace-tech/statespace/agents-md"><img src="https://agentmods.dev/badge/instructions/statespace-tech/statespace/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 | $0.00849 | $0.00849 |
| Opus 5.5 | $0.00340 | $0.00340 |
| Sonnet 5.5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
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 yesterday.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributor instructions
An experiment compares commits of one app. Each arm is one commit with an exact share
of the app's subjects. ssp app, ssp experiment, and ssp token call the
Statespace API. ssp proxy docker, ssp proxy cloudrun, ssp proxy kubernetes, ssp proxy fargate, and ssp proxy fly run a reverse proxy in front of the app's live service.
ssp proxy s3 and ssp proxy gcs serve a static site from a bucket: live is the
bucket root, and each arm is a build folder (src/proxy/orchestrator/files).
Every proxy instance routes requests to the arms of running experiments, in the order
of statespace.toml. Only the instance that holds the app's lease starts and stops
units, one for each arm of each starting or running experiment, through the
Orchestrator trait in src/proxy/orchestrator. On a file runtime, every instance
checks the build folders, because each instance serves the files itself.
../design/ is the source of truth for the model.
Rules
- Use
ssp <noun> <verb> <object>. The object is positional.--appnames the app of an experiment or a token. Leave it optional where the folder can tell the app.ssp proxytakes no--app: Statespace tells the app of the runtime token. - Run alongside live, never inside it: never change a resource that
sspdid not create. Each unit is a resource thatsspcreates, labels, and deletes. - Print text by default and exactly one JSON document with
--json, exceptssp proxy.--jsoncarries exactly the information of the text output, structured; never more. Send notes and warnings to standard error. Errors exit 1, as{"error": "..."}with--json. - Give
--note(1 to 200 characters, one line) to every command that changes something. - Keep settings in
statespace.toml. Add no proxy flag for a setting. - Keep commands noninteractive, except
ssp login. - Print secrets only in the response that creates them. Never pass
STATESPACE_*variables to units or live. ssp proxymust never block or slow the app: drop counts rather than wait, and send a request to live rather than fail it. Build an orchestrator from its flags alone, so the proxy serves live before Statespace names the app; the calls that report live or run units take theApp.- Never count live or overrides. Read no logs of units or live.
- Never change the bucket function: it would move the subjects of running experiments.
- Keep no legacy: when the design changes, remove the old way.
- Keep the starter
statespace.tomland the CI step inskills/statespace/SKILL.mdcurrent. There is nossp init. - Write docs, READMEs, and skills in Simplified Technical English. Never name customers.
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.
- yesterday Changed · +1 lines · +25 tokens per session adabee5d6f17
- 3d ago Changed · +8 lines · +171 tokens per session cf0f3e80d739
- 4d ago Changed · +4 tokens per session 8635e7866bfe
- 8d ago Changed · +15 lines · +232 tokens per session dc6d35caa45d
- 13d ago Changed · +7 tokens per session 517c69382297
- 16d ago Changed · +1 lines · +37 tokens per session c74137debea0
- 22d ago Changed · -201 lines · -2,113 tokens per session d59339040f68
- 2mo 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 (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 849 tokens to every session, about $0.0034 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.
statespace AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| statespace AGENTS.mdstatespace-tech/statespace | Instructions file | 1 | yesterday | Apache-2.0 | A | 849 | 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 | yesterday | 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 |