Borrowing it
Nothing to install: this file belongs to magnus919/hermes-droid. 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/magnus919/hermes-droid/main/AGENTS.mdgit clone --depth 1 https://github.com/magnus919/hermes-droidWrote 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/magnus919/hermes-droid/agents-md)<a href="https://agentmods.dev/instructions/magnus919/hermes-droid/agents-md"><img src="https://agentmods.dev/badge/instructions/magnus919/hermes-droid/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/magnus919/hermes-droid/agents-md"><img src="https://agentmods.dev/badge/instructions/magnus919/hermes-droid/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 | $0.00366 | $0.00366 |
| Opus 5.5 | $0.00146 | $0.00146 |
| Sonnet 5.5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
hermes-droid 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.
What it actually says
AGENTS.md
Purpose
This repository ships one portable Agent Skills bundle: factory-droid/. Keep it standalone, agent-agnostic, and grounded in Factory Droid's current CLI behavior.
Before Editing
- Read
factory-droid/SKILL.mdand the reference file affected by the change. - Verify CLI flags, model IDs, authentication behavior, or pricing claims against Factory documentation or the installed
droid --helpoutput. Do not preserve a claim merely because it existed in the upstream PR. - Keep
SKILL.mdconcise. Put conditional or detailed material infactory-droid/references/and link to it explicitly.
Conventions
factory-droid/SKILL.mdfrontmatter follows the public Agent Skills specification: only portable fields, no Hermes-specific metadata.- Documentation examples must be copyable shell commands and must not contain credentials.
- Use the safest autonomy level that can complete an example. Never normalize
--skip-permissions-unsafeoutside an isolated sandbox. - Do not add a wrapper, package, dependency, or configuration layer unless the upstream CLI cannot do the job directly.
- Keep human documentation in
README.md; keep contribution process inCONTRIBUTING.md.
Validation
Run this before every commit:
python3 scripts/validate.py
The checker confirms frontmatter boundaries and required fields, validates the directory/name match, checks required references, and detects broken local Markdown links. It intentionally uses only Python's standard library.
Pull Requests
- One coherent change per PR.
- Explain the source that verifies behavior changes.
- Include the validation command and its output in the PR body.
- Do not commit keys, session data, or generated CLI transcripts containing private repository details.
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 · 37 lines · 366 tokens per session scan A 2818d2fd33b0
hermes-droid AGENTS.md is an instructions file published in the GitHub repository magnus919/hermes-droid (7 stars, last pushed 4mo ago), licensed MIT. It adds 366 tokens to every session, about $0.0015 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.
hermes-droid AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hermes-droid AGENTS.mdmagnus919/hermes-droid | Instructions file | 7 | 4mo ago | MIT | A | 366 | 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 | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |