Octos is a self-hosted AI assistant that runs on a user's computer and can connect to different AI providers, execute code, browse the web, remember information, schedule jobs, and create documents through browser, terminal, and messaging interfaces. The catalogue entries extend or configure this assistant's workflows.
Borrowing it
Nothing to install: this file belongs to octos-org/octos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/octos-org/octos/main/AGENTS.mdgit clone --depth 1 https://github.com/octos-org/octosWrote 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/octos-org/octos/agents-md)<a href="https://agentmods.dev/instructions/octos-org/octos/agents-md"><img src="https://agentmods.dev/badge/instructions/octos-org/octos/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.
<a href="https://agentmods.dev/instructions/octos-org/octos/agents-md"><img src="https://agentmods.dev/badge/instructions/octos-org/octos/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00487 | $0.00487 |
| Opus 5.5 | $0.00195 | $0.00195 |
| Sonnet 5.5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
octos 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 1mo 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.
What it actually says
Working in Octos
Start with README.md, runtime architecture, and, for app hosts, the OctoSense integration walkthrough. See CLAUDE.md for build commands and .octos/AGENTS.md for release rules.
- Octos owns agent execution and OUP runtime contracts. A product host owns UI, app records and adapters and its app authorization policy. Keep that boundary explicit; tool declarations or model text do not themselves authorize access.
- Pin related Octos crates together in consumers. Distinguish this checkout from a consumer's selected revision in integration documentation.
- For host-owned app peers read
peers/app_binding.rs,peers/host_tools.rs,peers/turn_origin.rs,peers/shared_history.rsand their dispatcher call sites. Preserve workspace and memory binding, peer-token and connection ownership, context lifetime, tool confinement, reply correlation and origin checks. - A request context is a session, not a new peer. Shared history is a bounded projection between separate transcripts. Preserve tool-call pairing and do not merge transcripts or leak sibling context history as an incidental fix.
- Trace the actual frontend, transport, admitted turn, agent task and tool execution lifetimes.
OUP stdio's writer is a dedicated OS thread; the gateway
SessionActoris a separate runtime path. Honor the embedded API's 8 MiB worker-stack requirement. - Protocol changes must align the OUP specification, core types and codecs, dispatcher, capability advertisement, permissions and affected clients. Read the protocol specification.
- Run focused existing tests for changed behavior, including negative
authorization and cancellation cases where relevant. Repository-wide checks are
listed in README. For documentation changes, verify source links and symbols
and run
git diff --check. Record executed checks in the PR description. - Keep English and Chinese README entry points aligned. Preserve existing unrelated work and do not change consumer pins, deploy services or publish as part of a documentation correction unless requested.
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.
- 1mo ago First seen · 34 lines · 487 tokens per session scan A 52254cb27184
octos AGENTS.md is an instructions file published in the GitHub repository octos-org/octos (766 stars, last pushed today), licensed Apache-2.0. It adds 487 tokens to every session, about $0.0019 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 2026-10-03.
octos AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| octos AGENTS.mdoctos-org/octos | Instructions file | 766 | today | Apache-2.0 | A | 487 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |