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/murray17/rovai-ai/agents-mdgit clone --depth 1 https://github.com/murray17/rovai-aiWrote 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/murray17/rovai-ai/agents-md)<a href="https://agentmods.dev/instructions/murray17/rovai-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/murray17/rovai-ai/agents-md.svg" alt="Measured on agentmods" 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 | $0.00733 | $0.00733 |
| Opus 5 | $0.00367 | $0.00367 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
rovai-ai 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.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project documentation
- Documentation map, authority boundaries, and task-based reading rules:
docs/README.md. Read this first for architecture, implementation, planning, or documentation work. - Current version architecture and implementation status: follow the canonical
current_versionpointer andcurrentrow indocs/versions/README.md; do not hard-code a version path here. - When creating a version or changing
current_version, follow the canonical version transition checklist and record every conclusion in the new version overview. - Current cross-version architecture navigation:
docs/architecture/README.md; current authority and decision-rationale routing:docs/decisions/CURRENT.md; decision admission and historical governance:docs/decisions/README.md. - Do not create numbered ADR files. When adding or changing a Version Decision, Architecture, Contract, version document, or documentation route, run the generic documentation gates described in
docs/decisions/README.md#自动治理. Do not add feature-, version-, or Skill-specific checker exceptions. - Local environment, development run, tests, and macOS builds:
docs/development/README.md. - Before adding, merging, permanently disabling, or deleting Rust tests, follow the canonical Rust test admission and retirement policy.
- Before starting Electron,
rovai-core, a packaged App, or a real Runtime, read and followdocs/development/local-workflow.md. Usepnpm devrather than bareelectron-vite dev; never run the daily App fromdist/, and never point development or acceptance processes at daily ElectronuserData. - Do not treat historical version documents as current constraints, and do not infer implementation completion from historical decision status. Follow the conflict rules in
docs/README.md.
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 First seen · 36 lines · 733 tokens per session scan A a319a4b320ab
rovai-ai AGENTS.md is an instructions file published in the GitHub repository murray17/rovai-ai (46 stars, last pushed today), licensed MIT. It adds 733 tokens to every session, about $0.0037 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
Meldwork AGENTS.md
AGENTS.md instructions for Ryder-MHumble/Meldwork, covering meldwork development rules, working style, product boundaries, frontend and desktop and verification.
hermes-ai-team AGENTS.md
Instructions for smfworks/hermes-ai-team, covering mission, non-negotiable values (mirror docs/00-philosophy.md), how to consume this repo, working conventions and definition of done (for the phases in this repo).
ardur-agent AGENTS.md
AGENTS.md instructions for ArdurAI/ardur-agent, covering ardur agent session instructions, mandatory bootstrap, source hierarchy, session ownership rule and parallel session conduct.
factory CLAUDE.md
Instructions for squidbay/factory, covering you are the engineer seat of this factory, ⛔ preflight — prove access before you say a single word, boot order (every session, before anything else), first contact — when the factory is brand new and standing rules of this seat.
jockey CLAUDE.md
Instructions for recailai/jockey, covering claude.md, commands, development, architecture and file layout.
acp-forge AGENTS.md
Instructions for ky2renzzz/acp-forge, covering acp forge — agent instructions, project overview, architecture, conventions and build & test.