Borrowing it
Nothing to install: this file belongs to stasstepv/hermes-pwa. 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/stasstepv/hermes-pwa/main/AGENTS.mdgit clone --depth 1 https://github.com/stasstepv/hermes-pwaWrote 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/stasstepv/hermes-pwa/agents-md)<a href="https://agentmods.dev/instructions/stasstepv/hermes-pwa/agents-md"><img src="https://agentmods.dev/badge/instructions/stasstepv/hermes-pwa/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/stasstepv/hermes-pwa/agents-md"><img src="https://agentmods.dev/badge/instructions/stasstepv/hermes-pwa/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 | $0.01326 | $0.01326 |
| Opus 5.5 | $0.00530 | $0.00530 |
| Sonnet 5.5 | $0.00265 | $0.00265 |
| Haiku 4.5 | $0.00133 | $0.00133 |
Grade A, and why
hermes-pwa 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Hermes Mobile (hermes-pwa)
Onboarding for AI coding agents (and humans). This file stays thin on purpose — it points to the authoritative docs instead of duplicating them (duplication is what made the docs drift). Read this, then the linked file for details. If this file disagrees with the code, the code wins — fix this file.
What this project is
An independent, unofficial mobile-first PWA control plane for the self-hosted Hermes Agent, shipped
as a Hermes Dashboard plugin named hermes-pwa. From a phone: chat (streaming), approve/reject high-impact
actions, watch activity, browse kanban, view agents/system, install to home screen.
What it is NOT:
- not the Hermes desktop app (that's a separate product — visual reference only, never copy its code);
- not a fork of Hermes core — a thin plugin/client;
- not a place for secrets, API keys, model credentials, or agent logic;
- not affiliated with or endorsed by Nous Research (see
NOTICE).
Where to find what (authoritative docs)
| Topic | Source of truth |
|---|---|
| System map, structure, data flow, WS events, state machine, ADRs | ARCHITECTURE.md |
| TS/React conventions, naming, transport rules, perf budget | CODING_RULES.md |
| Fork/branch/PR flow, commit + DCO sign-off, quality gates, CI/CD, merge rules | CONTRIBUTING.md |
| Design tokens, theming, components | DESIGN_SYSTEM.md |
| Security model + known gaps | docs/SECURITY.md |
| Install / network / rollback | docs/INSTALL.md · docs/NETWORK_TAILSCALE.md · docs/ROLLBACK_AND_REINSTALL.md |
| Positioning, licensing, clean-room rationale | docs/THIRD_PARTY_CLIENT.md |
The three ground rules (non-negotiable)
- Clean-room. Build only against Hermes's public HTTP/WS API. Never copy source from the Hermes
desktop app (unlicensed) or any proprietary codebase. Protocol knowledge lives in
packages/core/src/transport/jsonrpc-contract.ts, reconstructed — not pasted. - Core/shell boundary.
packages/coreimports no React/DOM/window/document/navigator/CSS and nothing frompackages/web. Components never callfetch/new WebSocket— they go throughcorestores. Browser-only code lives underpackages/web/src/pwa/. Enforced by ESLintno-restricted-imports. - Security & privacy. No secrets in client code. No persisting credentials/tickets. High-impact actions
require explicit approval. Treat all server data as untrusted (no
dangerouslySetInnerHTML/eval). SeeCODING_RULES.md§8 anddocs/SECURITY.md.
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 · 84 lines · 1,326 tokens per session scan A f2246af07c3f
hermes-pwa AGENTS.md is an instructions file published in the GitHub repository stasstepv/hermes-pwa (37 stars, last pushed 1mo ago), licensed MIT. It adds 1,326 tokens to every session, about $0.0053 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-pwa AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hermes-pwa AGENTS.mdstasstepv/hermes-pwa | Instructions file | 37 | 1mo ago | MIT | A | 1,326 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | 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 copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |