Borrowing it
Nothing to install: this file belongs to arthurcoulston/helmo. 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/arthurcoulston/helmo/main/AGENTS.mdgit clone --depth 1 https://github.com/arthurcoulston/helmoWrote 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/arthurcoulston/helmo/agents-md)<a href="https://agentmods.dev/instructions/arthurcoulston/helmo/agents-md"><img src="https://agentmods.dev/badge/instructions/arthurcoulston/helmo/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/arthurcoulston/helmo/agents-md"><img src="https://agentmods.dev/badge/instructions/arthurcoulston/helmo/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 | $0.00587 | $0.00587 |
| Opus 5.5 | $0.00235 | $0.00235 |
| Sonnet 5.5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
helmo 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 29d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS — session routing for helmo
Canonical apparatus file (vendor-neutral). CLAUDE.md is a shim pointing here.
The context envelope is a design decision: what a session does NOT load is part
of its role.
One repository holds one product with three areas — Work, Roadmap and Runtime
— plus the core they share. A session reads the routing below, then the one file its
role names, then that area's DEV.md. Nothing else here.
What kind of session is this?
- Summoned role — meetings and the awaiting-human queue. Any request to
"summon the helmo orchestrator", run a meeting, or work the awaiting-human
queue: read
packages/work/HELMO-ORCHESTRATOR.mdwhole, to its last line, and reproduce its canary line before addressing any agenda. Read nothing else in this repository — notDEV.md, notsrc/. A meeting role that ingested the codebase is a worse meeting role. - Summoned role — the running machine. "Summon the watch officer", or any
request to inspect or control running loops: read
packages/runtime/WATCH-OFFICER.mdwhole, to its last line, and reproduce its canary line before acting. Read nothing else here — the watch officer operates sentinels and reads state; it does not need the TypeScript. - Coding / dev session — working on Helmo itself: read
DEV.mdfor what the whole product shares, then theDEV.mdof the area you are changing (packages/work,packages/roadmap,packages/runtime,packages/core). Before designing, prototyping, implementing or reviewing any Helmo UI, also readUI.md. shadcn/ui is the required component foundation across the app; matching its colors or tokens alone is not component adoption. - Agent using Helmo as a tool (MCP or CLI from anywhere else): the tool descriptions are self-sufficient; read nothing here.
- Loop sessions never start here — Runtime launches them in their own loop's cwd with their constitution injected; if that's you, your constitution already governs.
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.
- 29d ago Changed · +3 lines · +51 tokens per session 589cb4ec6fca
- 1mo ago Changed · +19 lines · +288 tokens per session 07ee3231d19f
- 2mo ago First seen · 22 lines · 248 tokens per session scan A 8e10ff6d56f5
helmo AGENTS.md is an instructions file published in the GitHub repository arthurcoulston/helmo (0 stars, last pushed 2d ago), licensed MIT. It adds 587 tokens to every session, about $0.0023 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 2026-08-31.
helmo AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| helmo AGENTS.mdarthurcoulston/helmo | Instructions file | 0 | 2d ago | MIT | A | 587 | 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 | yesterday | 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 |