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/off-grid-ai/ogam/agents-mdgit clone --depth 1 https://github.com/off-grid-ai/OGAMWhat 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 | $0.00132 | $0.00132 |
| Opus 5 | $0.00066 | $0.00066 |
| Sonnet 5 | $0.00026 | $0.00026 |
| Haiku 4.5 | $0.00013 | $0.00013 |
Grade A, and why
OGAM 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- OGAM CLAUDE.md — 94% identical, 2 lines differ
What it actually says
Agent Instructions
All rules for this repository live in rules.md — the single, tool-neutral source of
truth. This file is only a pointer so the rules stay identical no matter which agent reads them.
→ Read rules.md in full before doing anything. It covers repository layout, device
logs, branch/PR policy, copy & design standards, SOLID/architecture, platform abstraction, quality
gates, the testing doctrine, the push/review loop, and the on-device testing & verification playbook.
Do not add rules here. Add them to rules.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.
- 2d ago First seen · 11 lines · 132 tokens per session scan A c0aeabfbbc73
OGAM AGENTS.md is an instructions file published in the GitHub repository off-grid-ai/OGAM (3,034 stars, last pushed today), licensed MIT. It adds 132 tokens to every session, about $0.0007 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
OGAD CLAUDE.md
Claude Code instructions for off-grid-ai/OGAD, covering off grid ai desktop — agent guide, design — desktop-first, off grid brand, use the screen real estate — desktop density rules, what this app is and stack.
OGAD AGENTS.md
AGENTS.md instructions for off-grid-ai/OGAD, covering off grid ai desktop — agent guide, design — desktop-first, off grid brand, use the screen real estate — desktop density rules, what this app is and stack.
lilbee AGENTS.md
Instructions for tobocop2/lilbee, covering lilbee — development guide, before you write code (read this every time), project, task tracking (beads) and commands.
xyntetik-runner AGENTS.md
Instructions for Joakimpalm-Zen/xyntetik-runner, covering runner agent rules, the five defining rules, 1. deep modules, 2. tracer bullets and 3. tdd.
inferbench CLAUDE.md
Claude Code instructions for JoniMartin27/inferbench, covering instrucciones para claude code en este proyecto, antes de tocar nada, lo que no debes hacer (load-bearing), schemas de optimización son por motor, no uniformes and no simules motores.
llama-launcher CLAUDE.md
Instructions for airiclenz/llama-launcher: Consult llama-launcher.TDD.md for all project details: architecture, build commands, coding standards, and contribution workflow.