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/openagentsinc/openagents/agents-mdgit clone --depth 1 https://github.com/OpenAgentsInc/openagentsWhat 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 | $0.10190 | $0.10190 |
| Opus 5 | $0.05095 | $0.05095 |
| Sonnet 5 | $0.02038 | $0.02038 |
| Haiku 4.5 | $0.01019 | $0.01019 |
Grade C, and why
openagents AGENTS.md scanned grade C with 1 finding 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
IPC results, and visible UI. Never extract credentials as a diagnostic. Use How it starts
The opening of the file, as written. The whole thing — 693 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAgents Agent Contract
Scope
This repository owns the OpenAgents Rust CLI and retained supporting services,
contracts, and tools. The separate OpenAgentsInc/openagents.com repository
owns the sole current web application and backend, implemented in Phoenix.
The apps/openagents.com tree here is historical and must not receive current
web, API, or deployment work. It is deleted by the TypeScript-lane ledger
(docs/refactor/2026-08-28-typescript-lane-deletion-plan.md).
This repository is Rust-only. Do not add TypeScript. Phoenix and Elixir live
in OpenAgentsInc/openagents.com.
Preserve docs/transcripts/. It is the retained transcript archive from the
previous repository shape.
Simplified Technical English
- Use ASD-STE100 Issue 9 Simplified Technical English (STE) only for the
public documentation paths defined in
docs/ste/checker-config.v1.json. - Follow
docs/ste/README.mdfor profiles, source data, inspections, migration states, and the exact publication boundary. - Use the approved OpenAgents terms in the versioned glossary.
- Internal strategy, teardown, roadmap, audit, plan, specification, runbook, receipt, and agent working documents are outside STE governance. They can use the language and structure that best preserves technical meaning.
- Use the agent compact profile only for governed public agent-facing text when its controlled extensions make that text faster or less ambiguous.
- Do not apply the agent compact profile to public human-facing text.
- Do not copy the ASD dictionary into the repository. Use an authorized local dictionary for strict lexical checks.
- The completion gate does not run STE. Publication roots currently listed
in
docs/ste/checker-config.v1.jsonlive underapps/openagents.comand leave with that tree. Phoenix owns live public docs. - Run the STE check only when a changed file is in the configured public scope and you are still in a wave that contains that tree. Do not add a structural defect to a governed file in migration.
- Do not use an automatic text change for normative requirements, commands, identifiers, evidence values, or quoted source data.
- Keep the technical meaning during a conversion. Record a semantic comparison for authority, safety, privacy, payment, release, and acceptance text.
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 · 693 lines · 10,190 tokens per session scan C 3a324559dc2b
openagents AGENTS.md is an instructions file published in the GitHub repository OpenAgentsInc/openagents (446 stars, last pushed 2d ago), licensed Apache-2.0. It adds 10,190 tokens to every session, about $0.0509 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
airi copilot-instructions.md
Copilot instructions for moeru-ai/airi, covering copilot repository instructions, general rules, validation and output format.
entroly CLAUDE.md
Instructions for juyterman1000/entroly, covering claude.md, gstack operating protocol, default workflow, entroly trust invariants and review checklist.
autonomous-os AGENTS.md
Instructions for autonomous-ai/autonomous-os, covering agents.md, multi-ide rules, working style, parallel work / subagents and device access rules.
spellbook AGENTS.md
Instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
Codex-Skills AGENTS.md
Instructions for TheGoat395/Codex-Skills, covering repository operating notes, required checks, evidence rules and change hygiene.