Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/pierodn/gdevice/agents-mdgit clone --depth 1 https://github.com/pierodn/gdeviceWhat 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 | $0.01651 | $0.01651 |
| Opus 5 | $0.00826 | $0.00826 |
| Sonnet 5 | $0.00330 | $0.00330 |
| Haiku 4.5 | $0.00165 | $0.00165 |
Grade A, and why
gdevice 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 2d 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.
The source is not reproduced here
Licensed GPL-3.0
The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 2d ago First seen · 167 lines · 1,651 tokens per session scan A edcbecb2a9a4
gdevice AGENTS.md is an instructions file published in the GitHub repository pierodn/gdevice (11 stars, last pushed 1mo ago), licensed GPL-3.0. It adds 1,651 tokens to every session, about $0.0083 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 2026-08-30.
Other instructions, from other repositories
KLineChartQuant AGENTS.md
Instructions for 363045841/KLineChartQuant, covering trellis instructions, klinechartquant — agent guide, 代码要求, pr 作者要求 and quick search.
kart-royale CLAUDE.md
Instructions for ryancampbell/kart-royale, covering working on this repo, commands, the contract, traps that have already cost a round and verifying a change.
skyrim-community-shaders copilot-instructions.md
Copilot instructions for community-shaders/skyrim-community-shaders, covering github copilot instructions, primary documentation, project overview, environment and build essentials and windows-only requirements.
dcc-mcp-houdini AGENTS.md
Instructions for dcc-mcp/dcc-mcp-houdini, covering agents.md — dcc-mcp-houdini, agent control path, cli availability and updates, quick start (inside houdini) and skills-first workflow.
starling AGENTS.md
Instructions for starling-browser/starling, covering agents — rules of engagement, tl;dr, 1. orient, 2. claim something unblocked and 3. read the package file and start working on main.
dcc-mcp-houdini CLAUDE.md
Instructions for dcc-mcp/dcc-mcp-houdini, covering what this project does, claude desktop configuration, progressive loading — important for claude, claude-specific tips and quick test prompts.