agentos: Instructions file for Codex

AGENTS.md

agentos AGENTS.md is an instructions file for Codex, OpenCode from framerslab/agentos. It costs 1,998 tokens per session, scanned A, original, Apache-2.0.

A repository instruction guide for coding agents working on AgentOS, an open-source TypeScript runtime for AI agents. It describes the project layout, tools, commands, tests, documentation, and major systems such as memory, workflows, provider access, and safety.

In plain words
What is it for?
Use it when contributing to AgentOS, especially when changing its TypeScript runtime, agent orchestration, memory, safety, tools, or tests.
Why use it?
It gives agents the repository context and working rules needed to make changes in the right files and use the expected commands.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is framerslab/agentos's own configuration. It tells Codex and OpenCode how to work on agentos itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentos configures →

Reuse

Borrowing it

Nothing to install: this file belongs to framerslab/agentos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/framerslab/agentos/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/framerslab/agentos

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for agentos AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/framerslab/agentos/agents-md/github.svg)](https://agentmods.dev/instructions/framerslab/agentos/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/framerslab/agentos/agents-md"><img src="https://agentmods.dev/badge/instructions/framerslab/agentos/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.

agentmods 80×15 button for agentos AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/framerslab/agentos/agents-md"><img src="https://agentmods.dev/badge/instructions/framerslab/agentos/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,998 This file is loaded in full into every session.
When invoked 1,998 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01998 $0.01998
Opus 5.5 $0.00799 $0.00799
Sonnet 5.5 $0.00400 $0.00400
Haiku 4.5 $0.00200 $0.00200

Measured 5d ago against content hash 37ee1b781e40, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentos 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 5d 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.

AGENTS.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for coding agents working in this repository. People contributing by hand: see CONTRIBUTING.md.

What this is

@framers/agentos is an open-source TypeScript runtime for AI agents: cognitive memory, optional HEXACO personality, multi-agent orchestration, runtime tool forging and one interface across LLM providers. It is published to npm as an ESM package under Apache-2.0.

Repository map

  • src/api/: the high-level API (generateText, streamText, agent(), agency()) and its runtime
  • src/core/: LLM providers (src/core/llm/providers/), API-key pools (src/core/providers/), conversation, embeddings, guardrails, rate limiting, storage, streaming, tools, vector stores
  • src/cognition/: memory, RAG, emergent behavior, skills, web search
  • src/orchestration/: planners, the compiler, workflows, checkpoints, human-in-the-loop
  • src/io/: channels, speech, the voice pipeline, vision, avatars
  • src/safety/: guardrails, auth, sandbox, provenance, validation
  • src/extensions/: extension pack loading
  • src/agents/, src/config/, src/logging/, src/utils/
  • tests/ and src/**/__tests__/: vitest suites
  • docs/: guides; docs/publication-manifest.cjs decides which pages docs.agentos.sh publishes
  • examples/: runnable examples (.mjs and .ts)
  • scripts/: build and release helpers

Toolchain

CI uses Node 22 and pnpm 10. TypeScript with Bundler module resolution; the package is ESM ("type": "module").

Commands

CI runs the commands below, and its result decides. Run any of them locally to check a change before you push; the parts that run only on GitHub Actions are named where they occur.

CI runs (job "Test & Lint" in .github/workflows/ci.yml), in order:

  1. pnpm install
  2. node --test scripts/curated-extensions-peer.test.mjs (checks that the lockfile and the install resolve the AgentOS peer of the extensions registry and of every curated extension to this checkout, and that the lockfile resolves every other first-party peer of a curated package inside its range; see Conventions)
  3. pnpm run build (cleans dist, compiles, then rewrites path aliases and import specifiers in dist)
  4. pnpm run verify:exports (checks that every non-wildcard exports target exists in the build; on GitHub Actions it then installs the packed package into an empty project, where the meeting channel, safety runtime and checked egress entries compile and import with network access refused, and the release's prepublishOnly runs that same candidate check again before publishing; a CI run dispatched by hand on a release tag checks the published package of that version instead, after matching its tarball to the registry's integrity. Run locally, the command checks the exports map alone: the install checks are skipped off GitHub Actions)
  5. pnpm run lint
  6. pnpm run typecheck
  7. pnpm run test:coverage, the whole suite with coverage on, which fails below the thresholds in vitest.config.ts (Postgres-backed tests run only when AGENTOS_TEST_POSTGRES_URL is set; CI provides a Postgres service. The Moonshine browser provider's integration test runs only when AGENTOS_TEST_MOONSHINE_DIR is set, and is skipped with a note naming the file when the folder it names lacks one of the model's files or the clip, or holds one empty; CI fetches them before this step)

Read the full file on GitHub · 83 lines

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.

  1. 5d ago Changed · +51 tokens per session 37ee1b781e40
  2. 10d ago Changed · +18 tokens per session b3343eaed6e1
  3. 17d ago Changed · +1 lines · +151 tokens per session 6bf154ea320f
  4. 19d ago Changed · +2 lines · +203 tokens per session f9d270497d62
  5. 23d ago Changed · +1 lines · +142 tokens per session 99989904c1c4
  6. 24d ago Changed · +40 tokens per session 210b24353de6
  7. 1mo ago First seen · 79 lines · 1,393 tokens per session scan A ab5e11edd762

Subscribe to this mod's changes

agentos AGENTS.md is an instructions file published in the GitHub repository framerslab/agentos (683 stars, last pushed today), licensed Apache-2.0. It adds 1,998 tokens to every session, about $0.0080 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 2026-10-06.

Related

agentos AGENTS.md compared with instructions from other repositories

agentos AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agentos AGENTS.mdframerslab/agentosInstructions file683todayApache-2.0A1,998Codex, OpenCode
plan-forge frontend.instructions.mdsrnichols/plan-forgeInstructions file62d agoMITA1,485GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot