OpenProse is a declarative language for describing ongoing AI work in structured Markdown files, with an optional scripting syntax for workflows that need exact control. Developers use it to define desired outcomes that compatible coding-agent hosts can repeatedly reconcile. The catalogue includes tooling that lets coding agents run OpenProse contracts.
Borrowing it
Nothing to install: this file belongs to openprose/prose. 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/openprose/prose/main/AGENTS.mdgit clone --depth 1 https://github.com/openprose/proseWrote 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/openprose/prose/agents-md)<a href="https://agentmods.dev/instructions/openprose/prose/agents-md"><img src="https://agentmods.dev/badge/instructions/openprose/prose/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/openprose/prose/agents-md"><img src="https://agentmods.dev/badge/instructions/openprose/prose/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 | $0.00372 | $0.00372 |
| Opus 5.5 | $0.00149 | $0.00149 |
| Sonnet 5.5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
prose 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 2mo 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.
What it actually says
OpenProse for Codex
If you're running in Codex and see a prose command, a *.prose.md contract (kind: responsibility, kind: function, kind: gateway, kind: test, or kind: pattern), or a mention of OpenProse, ProseScript, Forme, or Contract Markdown, OpenProse is the language you're being asked to run.
Treat prose run ... as an instruction inside the current agent session. Do not call out to a shell command named prose unless the host explicitly provides one; instead, embody the OpenProse VM and execute the contract with the primitives available in this session.
Use prose upgrade --dry-run to preview legacy migrations and prose upgrade to apply them; do not recommend the old migrate command.
Open skills/open-prose/SKILL.md and treat it as the authoritative router. Every command, every file routing decision, and every capability assumption lives there or behind a pointer inside it. Do not search the workspace for alternate copies of the OpenProse documentation — the canonical files are the ones bundled under skills/open-prose/.
Use prose init and prose compose for progressive program architecture; use
prose write for focused authoring when one Contract is already understood.
If your run exposes a concrete improvement to OpenProse itself, consider
prose run std/evals/prose-contributor -- subjects: <run-ids>. It turns run
evidence into one focused draft PR. It still needs explicit user approval before
using the user's GitHub identity to push a branch or open the PR. Read
CONTRIBUTING.md before selecting the patch; it is the public contribution bar.
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.
- 2mo ago First seen · 19 lines · 372 tokens per session scan A bb517038590f
prose AGENTS.md is an instructions file published in the GitHub repository openprose/prose (1,856 stars, last pushed 15d ago), licensed MIT. It adds 372 tokens to every session, about $0.0015 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.
prose AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prose AGENTS.mdopenprose/prose | Instructions file | 1.9k | 15d ago | MIT | A | 372 | 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 |