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/robium-ai/robium/agents-mdgit clone --depth 1 https://github.com/robium-ai/robiumWhat 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 | $0.00719 | $0.00719 |
| Opus 5 | $0.00360 | $0.00360 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
robium 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 2d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Canonical guidance for Codex, Claude Code, and other coding agents working in this repository.
Repository purpose
robium ships a native robotics-skills plugin plus its CLI and learning engine. The plugin is knowledge and real reusable examples, not an application framework or invented DSL.
skills/,hooks/,agents/,.codex-plugin/,.claude-plugin/: plugin.cli/: therobium-ainpm package.learnings/,scripts/engine/: evidence capture and skill hardening.archive/: immutable snapshots of prior skill versions.docs/: history, architecture notes, and changelog.
Applications live in the sibling robium-ai/robium-apps repository. The site
and live-demo orchestrator live in robium-ai/robium-website. Make changes in
the repository that owns the output; cross-reference rather than duplicate.
Maintainer collaboration
- An explicit, bounded change request authorizes implementation after reading the affected code. Give a short work update, then proceed; do not announce a process classification or ask for the same approval twice.
- For a new application or material architecture change, present one rough direction with meaningful alternatives. Once approved, implement and verify without further conversational gates.
- Pause only when a missing choice materially changes the result, scope must expand, or safety/external authority requires confirmation.
- Prefer the cheapest risk-reducing probe and the first user-visible working slice before polishing infrastructure or optimizing scale.
Modes and ownership
- Skill authoring: follow
skills/AGENTS.mdand loadskill-author. - Learning engine: follow
learnings/AGENTS.mdand loadlearning-loop. - Application build/QA: work in
robium-apps; hooks capture evidence silently here. Do not interrupt the build to edit skills. - CLI: work under
cli/; publish only from that directory and only with explicit authorization. - Website/demo infrastructure: work in
robium-websiteunder its guidance.
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.
- 2d ago First seen · 73 lines · 719 tokens per session scan A c94f0a13e6ae
robium AGENTS.md is an instructions file published in the GitHub repository robium-ai/robium (9 stars, last pushed 4d ago), licensed MIT. It adds 719 tokens to every session, about $0.0036 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 2026-08-31.
Other instructions, from other repositories
missionos AGENTS.md
Instructions for pome223/missionos, covering agent instructions, documentation layers, claim boundaries, public safety and pull request verification.
claude-ros2-skills CLAUDE.md
Instructions for Leehyunbin0131/claude-ros2-skills, covering read this first — ros 2 verification protocol, establish before writing (no doc can tell you these) and done means it ran.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.