Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/lesterppo/hermes-gem-pw/agents-md)<a href="https://agentmods.dev/instructions/lesterppo/hermes-gem-pw/agents-md"><img src="https://agentmods.dev/badge/instructions/lesterppo/hermes-gem-pw/agents-md.svg" alt="Measured on agentmods" 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 | $0.01492 | $0.01492 |
| Opus 5 | $0.00746 | $0.00746 |
| Sonnet 5 | $0.00298 | $0.00298 |
| Haiku 4.5 | $0.00149 | $0.00149 |
Grade A, and why
hermes-gem-pw 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 5d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Hermes Agent Guide
What This Tool Does
gem-pw is a browser-automated CLI for interacting with Gemini Gems. It
bypasses gemini-webapi's broken RPC authentication by driving the real Gemini
web UI through a Chromium browser (CDP-first, headed fallback).
One tool. This repo ships only gem-pw. The older gem.py is superseded
and removed.
When an Agent Should Use This
- User shares a Gemini Gem link (
gemini.google.com/gem/...). gemini-webapiorgem-clireturns UNAUTHENTICATED / timeout.- Need to chat, create, edit, delete Gems, upload files, or generate images.
- Need multi-turn conversation with memory across turns.
- Need token-efficient code/design iteration via
--collabsurgical diffs. - Need Pro + Extended Thinking with large knowledge bases.
How to Invoke
# Chat
gem-pw <gem-id> "prompt"
gem-pw <gem-id> -c sess.json "prompt" # Multi-turn
gem-pw <gem-id> -m pro --thinking extended -t 600 "deep"
# Surgical-diff iteration (token-efficient)
gem-pw --collab <gem-id> -f file "instruction" -o resp.md -t 300
python3 apply_gem_diff.py resp.md file # apply
python3 apply_gem_diff.py resp.md file --dry # preview
# Gem CRUD
gem-pw --create "Name" "Instructions" -m pro --thinking extended
gem-pw --create "Name" "Instr" \
--knowledge-file paper.pdf \
--knowledge-code https://github.com/user/repo \
--knowledge-folder /path/to/project
gem-pw --edit <gem-id> --name "New Name"
gem-pw --edit <gem-id> --instructions "New prompt..."
gem-pw --edit <gem-id> --knowledge-code https://github.com/user/repo
gem-pw --edit <gem-id> -m pro --thinking extended
gem-pw --delete <gem-id>
# Upload / Image
gem-pw --upload <gem-id> -f file "Q"
gem-pw --img <gem-id> "description"
# Help
gem-pw --help
Setup (one-time)
pip install playwright aiohttp
playwright install chromium
gem-pw-login # Opens Chromium window — sign into Gemini (needs X display)
Optionally start a persistent CDP browser for the fast path:
cr-server start --headed (listens on http://127.0.0.1:9223).
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.
- 5d ago First seen · 149 lines · 1,492 tokens per session scan A 114a8f963a50
hermes-gem-pw AGENTS.md is an instructions file published in the GitHub repository lesterppo/hermes-gem-pw (1 stars, last pushed 28d ago), licensed MIT. It adds 1,492 tokens to every session, about $0.0075 per session on Opus 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.
Other instructions, from other repositories
moli AGENTS.md
AGENTS.md instructions for lexmount/moli: Before committing changes that modify Rust source code or Rust build metadata (such as Cargo.toml, Cargo.lock, or rust-toolchain), run all of the following from the repository root and ensure they pass.
apitap CLAUDE.md
Instructions for n1byn1kt/apitap, covering claude.md, using apitap as an mcp tool, commands, architecture and module map.
fanqie-publisher-skill AGENTS.md
Instructions for amm10090/fanqie-publisher-skill, covering fanqie-publisher-skill — codex cli agent adapter, read first, prerequisites, entry points and utf-8 / unicode safeguards.
fanqie-publisher-skill CLAUDE.md
Instructions for amm10090/fanqie-publisher-skill, covering fanqie-publisher-skill — claude code adapter, read first, entry points, prerequisites and utf-8 / unicode safeguards.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
claude-browser-test-skills CLAUDE.md
Instructions for Autodesk/claude-browser-test-skills, covering claude.md, what this repo is, layout, conventions when editing skills and validate before publishing.