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/openmodelingfoundation/openmodelingfoundation.github.io/agents-mdgit clone --depth 1 https://github.com/openmodelingfoundation/openmodelingfoundation.github.ioWhat 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 | $0.00556 | $0.00556 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
openmodelingfoundation.github.io 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
Repository-specific constraints for AI agents working on the Open Modeling Foundation Hugo + Docsy site (GitHub Pages).
Contributor documentation: README.md.
Precedence
If instructions conflict: AGENTS.md → adapter files (CLAUDE.md, .github/copilot-instructions.md) → README.md.
Invariants
- Run all project commands inside the Docker Compose
hugoservice viamaketargets. Do not use host-installed tooling. If a command cannot run in the container, explain why and propose a container-based alternative. - Edit authoritative sources, then regenerate.
data/publications.jsonis generated fromassets/bibliographies/publications.bibvia.github/scripts/bibtex_to_json.py. public/is build output. Never edit it directly.- Never commit deploy credentials, API tokens, or analytics keys. Deployment secrets live in GitHub Actions repository secrets.
Commands
Prefer make targets. Use Docker Compose directly only when debugging the build system.
| Need | Use |
|---|---|
| Preview site locally | make serve |
| Production-style render | make render |
| Render while another Hugo container is running | make render-site-isolated |
| Regenerate publications JSON from BibTeX | make publications-json |
| CI-equivalent production build | .github/scripts/build-site.sh |
Deployment
Pushes to develop trigger the GitHub Pages workflow (.github/workflows/gh-pages.yml). The repository Pages source must be set to GitHub Actions, not a branch.
Hugo gotchas
Module mounts
When modifying hugo.yaml mounts, always include an explicit static -> static mount. Hugo drops the implicit default static/ → public/ copy when any mount is defined, silently removing static assets from the build.
Font declarations
Place @font-face rules in a Hugo template partial (layouts/partials/hooks/head-end.html), not in SCSS. Hugo template functions like relURL are unavailable in the SCSS toCSS pipeline.
Asset paths
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 · 52 lines · 556 tokens per session scan A 4379efa36ca2
openmodelingfoundation.github.io AGENTS.md is an instructions file published in the GitHub repository openmodelingfoundation/openmodelingfoundation.github.io (53 stars, last pushed 10d ago), licensed CC0-1.0. It adds 556 tokens to every session, about $0.0028 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
cryocore AGENTS.md
Instructions for BioSymphony/cryocore, covering biosymphony cryocore agent guide, operating rules, ownership boundary, dev commands and key patterns and conventions.
LongTable AGENTS.md
Instructions for HosungYou/LongTable, covering agents.md, purpose, working rules, editing rules and required supporting docs.
wisp-science AGENTS.md
AGENTS.md instructions for xuzhougeng/wisp-science, covering agents.md, project orientation, repository layout, engineering rules and verification commands.
MoleCode AGENTS.md
Instructions for AtomFlow-AI/MoleCode, covering agents.md — molecode, what this repo is, use the molecode skill, molecode-first rule and cli quick start.
ami-mcp CLAUDE.md
Claude Code instructions for kratsg/ami-mcp, covering ami-mcp — contributor guide, architecture, project layout, tool registration pattern and tools/mymodule.py.
symkit-mcp CLAUDE.md
Instructions for LBurny/symkit-mcp, covering claude.md - claude code project guide, project overview, core tools, usage patterns and stateless quick calculation.