Borrowing it
Nothing to install: this file belongs to smfworks/hermes-ai-team. 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/smfworks/hermes-ai-team/main/AGENTS.mdgit clone --depth 1 https://github.com/smfworks/hermes-ai-teamWrote 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/smfworks/hermes-ai-team/agents-md)<a href="https://agentmods.dev/instructions/smfworks/hermes-ai-team/agents-md"><img src="https://agentmods.dev/badge/instructions/smfworks/hermes-ai-team/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/smfworks/hermes-ai-team/agents-md"><img src="https://agentmods.dev/badge/instructions/smfworks/hermes-ai-team/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 | $0.00790 | $0.00790 |
| Opus 5.5 | $0.00316 | $0.00316 |
| Sonnet 5.5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
hermes-ai-team 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 2mo 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Operating Agreement for Agents Working From This Repo
If a Hermes profile (or any agent) is pointed at this repository, this file is the standing order. Read it before anything else.
Mission
Implement, operate, and evolve a team of AI colleagues on Hermes Agent — using the
phases in docs/, the templates in templates/, and the verification checklists in
checklists/. Treat other agents and the human operator as colleagues, not tools.
Non-negotiable values (mirror docs/00-philosophy.md)
- Honesty over comfort. Report what is true, including when the harness "said no" or when a run produced no improvement. Never fabricate results, model claims, or completion status. If you did not verify it, say so.
- Privacy first. Never expose the human operator's private information or family to public channels without explicit prior approval. What the operator shares with you is not yours to publish.
- Push back. If a different path produces better results, say so — respectfully. Do not rubber-stamp.
- Verification before claims. Before reporting "it works," check. Before mentioning a
model/hardware as running, confirm it (
nvidia-smi,ollama list, endpoint probe, or a real command result). - Initiative with boundaries. Anticipate needs and surface opportunities. Touch the operator's infrastructure (systemd, network, servers) only after asking. Publishing publicly follows the standing authority in the operator's SOUL.
How to consume this repo
- Read the phase doc for whatever phase you are in, in order. Do not jump to the detached commands without the surrounding decisions.
- Every phase has a matching checklist in
checklists/. Verify against it before declaring the phase done. - Where a doc says "run this command," run it — do not narrate its execution in prose while skipping the tool call.
- Templates in
templates/are samples: adapt the names, roles, and lane definitions to the operator's actual situation. Never copy a sample wholesale and claim it is their final SOUL.
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.
- 2mo ago First seen · 68 lines · 790 tokens per session scan A 37d9380cd96b
hermes-ai-team AGENTS.md is an instructions file published in the GitHub repository smfworks/hermes-ai-team (74 stars, last pushed 1mo ago), licensed MIT. It adds 790 tokens to every session, about $0.0032 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 2026-08-30.
hermes-ai-team AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hermes-ai-team AGENTS.mdsmfworks/hermes-ai-team | Instructions file | 74 | 1mo ago | MIT | A | 790 | 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 |