Borrowing it
Nothing to install: this file belongs to PrimeIntellect-ai/nano-rlm. 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/PrimeIntellect-ai/nano-rlm/main/AGENTS.mdgit clone --depth 1 https://github.com/PrimeIntellect-ai/nano-rlmWrote 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/primeintellect-ai/nano-rlm/agents-md)<a href="https://agentmods.dev/instructions/primeintellect-ai/nano-rlm/agents-md"><img src="https://agentmods.dev/badge/instructions/primeintellect-ai/nano-rlm/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/primeintellect-ai/nano-rlm/agents-md"><img src="https://agentmods.dev/badge/instructions/primeintellect-ai/nano-rlm/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 | $0.00458 | $0.00458 |
| Opus 5.5 | $0.00183 | $0.00183 |
| Sonnet 5.5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
nano-rlm 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 6d 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
AGENTS.md
Writing code
- Minimal try/except: let errors propagate — silent failures hide bugs. Only catch for intentional fault tolerance (retries, robustness).
- Targeted comments: don't explain your work process or reference old code. Use comments sparingly to clarify ambiguous logic or non-obvious constraints.
- No "this replaced that" comments: never write comments or docstrings that reference code that used to exist. That context belongs in the PR, not in the file. Describe what the code does now, not what it isn't anymore.
Docs
- Keep docs current: user-facing behavior is documented in
docs/(indexed from the README). A change to that behavior updates the page that describes it in the same PR.
Running code
- Always use uv: run code with
uv run, never rawpython. - Adding dependencies: add to
pyproject.tomland runuv sync(oruv sync --group devfor dev-only) to install and lock.
Testing
- Run the suite with
uv run pytest tests/. - Write tests as plain functions; don't use class-based tests.
- Conservative test additions: don't add new tests unless the user asks or it's clearly necessary. Editing existing tests is fine.
- Test what matters: only test code with clear, isolated logic. If you need to patch everything to make it testable, it's probably not worth testing.
Git
- Branch prefixes: use
feat/,fix/,chore/,docs/,tests/.
GitHub
- Draft PRs: always create PRs as drafts (
gh pr create --draft) to avoid triggering CI unnecessarily. - PR titles: start the title with a conventional-commit prefix matching the branch prefix (
feat:,fix:,chore:,docs:,tests:), e.g. adocs/...branch gets adocs: ...title. - Pull requests: do not include a "test plan" section unless you actually ran tests or the user explicitly asked for one.
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.
- 6d ago Changed · +4 lines · +42 tokens per session ebcc2ad0acd5
- 2mo ago First seen · 30 lines · 416 tokens per session scan A 99e8963c0762
nano-rlm AGENTS.md is an instructions file published in the GitHub repository PrimeIntellect-ai/nano-rlm (74 stars, last pushed yesterday), licensed MIT. It adds 458 tokens to every session, about $0.0018 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.
nano-rlm AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nano-rlm AGENTS.mdPrimeIntellect-ai/nano-rlm | Instructions file | 74 | yesterday | MIT | A | 458 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |