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/leandre755/gui_agent/agents-mdgit clone --depth 1 https://github.com/leandre755/gui_agentWhat 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 | $0.02187 | $0.02187 |
| Opus 5 | $0.01094 | $0.01094 |
| Sonnet 5 | $0.00437 | $0.00437 |
| Haiku 4.5 | $0.00219 | $0.00219 |
Grade A, and why
gui_agent AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories β prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency β measured yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- gui_agent CLAUDE.md β 97% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing β 225 lines β stays where its author put it; the contents beside it link to each section on GitHub.
Git-Context-Controller (GCC) Protocol
This protocol governs context persistence, architecture tracking, and session handoff mechanics. It must be strictly executed by the AI agent at specific session milestones.
<file_matrix> Acts as the global project registry. Contains high-level milestones, objective, chronological decision log, and an active index of valid plans. Step-by-step tactical implementation plan for complex, multi-session epics only. Factual technical changelog and precise transition state. Overwritten at the absolute end of every session to ensure seamless state-recovery in fresh chat environments. Persistent test execution log, tracking completed tests, results, bugs found, and fixes applied. Test backlog tracking all pending scenarios and test suites to be executed. </file_matrix>
<event_driven_protocols>
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.
- yesterday First seen Β· 225 lines Β· 2,187 tokens per session scan A 0ee79636bfe0
gui_agent AGENTS.md is an instructions file published in the GitHub repository leandre755/gui_agent (4 stars, last pushed 4d ago), licensed MIT. It adds 2,187 tokens to every session, about $0.0109 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
tuxevil-rotator CLAUDE.md
Instructions for tuxevil/tuxevil-rotator: This project uses AGENTS.md as the single source of truth for agent instructions.
clickup-mcp CLAUDE.md
Claude Code instructions for Npab19/clickup-mcp, covering claude.md β clickup mcp server, what this is, the one rule, clickup api facts that trip people up and adding a tool.
helix-pilot AGENTS.md
Instructions for tsunamayo7/helix-pilot, covering agents.md β helix-pilot, shared memory (mem0), connection spec (must match across all tools), http api (for codex cli, curl, scripts) and search.
helix-pilot CLAUDE.md
Instructions for tsunamayo7/helix-pilot, covering claude.md β helix-pilot, γγγΈγ§γ―γζ¦θ¦, ζθ‘γΉγΏγγ―, ε ±ζθ¨ζΆοΌmem0οΌ and ιηΊγ«γΌγ«.
openclaw-godot AGENTS.md
Instructions for GambitGamesLLC/openclaw-godot, covering agent instructions, quick reference, non-interactive shell commands, force overwrite without prompting and for recursive operations.
toh-framework CLAUDE.md
Instructions for wasintoh/toh-framework, covering claude.md β toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.