Borrowing it
Nothing to install: this file belongs to OpenHands/extensions. 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/OpenHands/extensions/main/AGENTS.mdgit clone --depth 1 https://github.com/OpenHands/extensionsWrote 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/openhands/extensions/agents-md)<a href="https://agentmods.dev/instructions/openhands/extensions/agents-md"><img src="https://agentmods.dev/badge/instructions/openhands/extensions/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/openhands/extensions/agents-md"><img src="https://agentmods.dev/badge/instructions/openhands/extensions/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 | $0.05312 | $0.05312 |
| Opus 5.5 | $0.02125 | $0.02125 |
| Sonnet 5.5 | $0.01062 | $0.01062 |
| Haiku 4.5 | $0.00531 | $0.00531 |
Grade A, and why
extensions AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `skills/bitbucket` should not tell agents to rewrite remotes proactively. In OpenHands, `BITBUCKET_TOKEN` is commonly kept in unencoded `user:token` form for API calls like `curl --user "$BITBUCKET_TOKEN" ...`; only sp How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenHands Extensions — Agent Notes
This repository (OpenHands/extensions) is the public extensions registry for OpenHands.
It contains shareable skills and plugins that can be loaded by OpenHands (CLI/GUI/Cloud) and by client code using the Software Agent SDK.
Cross-Repository Boundaries
This repository owns the public registry of reusable OpenHands skills, plugins, Agent Canvas Apps, automations, and integrations. These extensions are consumed by OpenHands applications and SDK-based clients.
Related repositories have distinct responsibilities:
OpenHands/software-agent-sdkowns the Python SDK, Agent Server, agent/tool behavior, conversations, workspaces, events, canonical API, and browser-compatible TypeScript Agent Server client underclients/typescript/.OpenHands/OpenHandsowns Agent Canvas UI and local-stack orchestration.OpenHands/automationowns scheduling, webhooks, run history, dispatch, and sandbox lifecycle orchestration.
Put reusable skills, plugins, automations, and integrations here; put backend execution behavior and typed API access in the SDK, application UI in Agent Canvas, and scheduling/dispatch lifecycle code in automation. If a PR is opened in the wrong repository, explicitly recommend closing and moving it to the owning repository. PRs must follow this repository's applicable contribution and code-review guidance.
Review-Facing Extension Checklist
Before opening a PR:
- Keep a content change focused on one skill, plugin, automation bundle, or integration. Put shared product runtime behavior in the repository that owns it instead of copying machinery into extension content.
- Treat every command, import, environment variable, endpoint, setup step, and package name as an executable contract. Test the documented entrypoint with released packages in each local or cloud environment the extension claims to support; do not rely on developer-only variables or private paths.
- For event-, comment-, or message-triggered work, define who may trigger it, whose identity executes it, what scope it may mutate, and which minimal secrets it receives. A trigger phrase is not authorization.
- Edit the hand-authored source once and regenerate derived catalogs, commands, indexes, and package assets with the existing sync/build command. Document the true generation direction and do not introduce a parallel source of truth.
- Verify copy-paste commands and factual documentation claims against the actual tool or authoritative source. Extension instructions are executed by agents, so incorrect setup or data-flow documentation is a functional defect.
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.
- yesterday Changed · -1 lines · +36 tokens per session 9fefa690e4f1
- 11d ago Changed · +2 lines · +124 tokens per session 3c6457405012
- 12d ago Changed · +33 lines · +434 tokens per session c8973db75c74
- 21d ago Changed · +1 lines · +36 tokens per session 67ab61bb4a5c
- 1mo ago Changed · +5 lines · +120 tokens per session d71111c39c77
- 1mo ago Changed · +1 lines · +117 tokens per session 0e3043fe8b66
- 1mo ago Changed · +9 lines · -78 tokens per session b8a5e45e1b1e
- 1mo ago Changed · +21 lines · +256 tokens per session c992b9200d10
- 1mo ago Changed · +25 lines · +280 tokens per session 6b4902673463
- 1mo ago First seen · 150 lines · 3,987 tokens per session scan A 13448242833e
extensions AGENTS.md is an instructions file published in the GitHub repository OpenHands/extensions (178 stars, last pushed today), licensed MIT. It adds 5,312 tokens to every session, about $0.0212 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
extensions AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| extensions AGENTS.mdOpenHands/extensions | Instructions file | 178 | today | MIT | A | 5,312 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |