Borrowing it
Nothing to install: this file belongs to RobinOppenstam/sema-evals. 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/RobinOppenstam/sema-evals/main/AGENTS.mdgit clone --depth 1 https://github.com/RobinOppenstam/sema-evalsWrote 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/robinoppenstam/sema-evals/agents-md)<a href="https://agentmods.dev/instructions/robinoppenstam/sema-evals/agents-md"><img src="https://agentmods.dev/badge/instructions/robinoppenstam/sema-evals/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/robinoppenstam/sema-evals/agents-md"><img src="https://agentmods.dev/badge/instructions/robinoppenstam/sema-evals/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 | $0.00286 | $0.00286 |
| Opus 5.5 | $0.00114 | $0.00114 |
| Sonnet 5.5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
sema-evals 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
Repository instructions
This repository evaluates semantic coordination mechanisms. Treat research validity as a product requirement.
Non-negotiable experiment rules
- Never describe deterministic harness output as evidence that Sema improves model performance.
- Keep pattern content identical between equal-information prose and Sema conditions. Isolate content, addressing, and enforcement effects.
- Choose and document one primary endpoint before a confirmatory run.
- Preserve every run, including failures, timeouts, and malformed outputs.
- Record prompt, dataset, model, implementation, Sema version, vocabulary root, scorer, and protocol fingerprints in result manifests.
- Report wire bytes, hydration/context tokens, and total model tokens separately. A short reference is not automatically a context-token saving.
- Prefer deterministic validators. Blind subjective judges to the experiment condition and never use an LLM judge as the only scorer.
- Do not use live trading capital in an experiment. Historical replay and paper execution come first.
Engineering rules
- Use pnpm and Node.js 22 or newer.
- Keep TypeScript strict and avoid
any. - Put reusable code in
packages/; experiment-specific policy belongs underexperiments/. - Generated result bundles belong under
results/and remain untracked unless intentionally promoted into a dated public report. - Run
pnpm checkbefore handing off changes.
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 · 32 lines · 286 tokens per session scan A fa46a2ee0d53
sema-evals AGENTS.md is an instructions file published in the GitHub repository RobinOppenstam/sema-evals (5 stars, last pushed 3mo ago), licensed MIT. It adds 286 tokens to every session, about $0.0011 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 2026-08-31.
sema-evals AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sema-evals AGENTS.mdRobinOppenstam/sema-evals | Instructions file | 5 | 3mo ago | MIT | A | 286 | 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 |