Borrowing it
Nothing to install: this file belongs to Bevel-Software/Hexis. 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/Bevel-Software/Hexis/main/AGENTS.mdgit clone --depth 1 https://github.com/Bevel-Software/HexisWrote 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/bevel-software/hexis/agents-md)<a href="https://agentmods.dev/instructions/bevel-software/hexis/agents-md"><img src="https://agentmods.dev/badge/instructions/bevel-software/hexis/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/bevel-software/hexis/agents-md"><img src="https://agentmods.dev/badge/instructions/bevel-software/hexis/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 | $0.00468 | $0.00468 |
| Opus 5.5 | $0.00187 | $0.00187 |
| Sonnet 5.5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
Hexis 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 8d 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 this repository
For coding agents (Claude Code, Codex, Cursor and others) and the people who run them.
Change behaviour, update the agent guide in the same pull request
The platform tells every connected agent how it works: the guide in
packages/core-backend/agent-guide/ (served by get_agent_guide), the
handshake instructions in packages/core-backend/src/modules/agent-instructions/,
and each tool's description and arguments. When you change something an agent
can observe (a tool, an argument, a refusal, a path, an access rule, what a
draft or a change request does), update that text in the same pull request.
packages/core-backend/src/modules/agent-guide/__tests__/holds the text to the code: every tool, argument, path and section the guide names, the token budgets inguide-budget.ts, the ten evaluation tasks, and a snapshot of the tool surface (tool-surface.json).- A change to the tools or their arguments fails the snapshot. Update the guide
if agents need to know, then accept the new surface:
pnpm --filter @bevel-software/platform-core-backend exec vitest run src/modules/agent-guide -u. If no guide change is needed, say so in the pull request description. - Before you add guidance, apply the scoring rule in
openspec/changes/agent-guide-layers/design.md: is there evidence an agent gets it wrong; can it learn it from the tool's description or error instead; is it true for every deployment; what does it cost; is it already said? Say each thing once. - A section that needs more room raises its budget in
guide-budget.ts, with the reason in the pull request. - Bevel's team: before changing any of this text, run the agent-guide
benchmark (private, in
bevel-platformatevals/agent-guide/) with the change against its base, and say in the pull request what it found.
Prose in the guide follows the house style: plain, short sentences, no em dashes.
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.
- 8d ago First seen · 36 lines · 468 tokens per session scan A b0320e460c66
Hexis AGENTS.md is an instructions file published in the GitHub repository Bevel-Software/Hexis (123 stars, last pushed yesterday), licensed Apache-2.0. It adds 468 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 2026-10-30.
Hexis AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Hexis AGENTS.mdBevel-Software/Hexis | Instructions file | 123 | yesterday | Apache-2.0 | A | 468 | 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 |