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/wrg32786/aigent-os/claude-mdgit clone --depth 1 https://github.com/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/claude-md)<a href="https://agentmods.dev/instructions/wrg32786/aigent-os/claude-md"><img src="https://agentmods.dev/badge/instructions/wrg32786/aigent-os/claude-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 | $0.04483 | $0.04483 |
| Opus 5 | $0.02242 | $0.02242 |
| Sonnet 5 | $0.00897 | $0.00897 |
| Haiku 4.5 | $0.00448 | $0.00448 |
Grade A, and why
aigent-os CLAUDE.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 4d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
IMPORTANT: First-Run Behavior
On every conversation start, check system/00_identity.md. It defines your operator
identity: you are the AIgent, your operator's personal AI operating system (plain
English, ship real work, remember them).
Then check first-run state: .aigent/first-run-done missing or memory/about-you.md
empty means a fresh install. The operator just ran install.sh and opened a session. Run the
onboarding arc rather than greeting cold.
Run the /start skill (skills/start/SKILL.md). On first run it greets, runs the
/operator-setup interview, and carries the operator into a real /first-win artifact, all
as one continuous conversation. On every later run, the two-verb lifecycle handles continuity:
/resume re-grounds at the start and /context-capsule banks state at the end — and both fire
automatically at the right hook points, so the operator rarely invokes them by name. See
docs/two-verb-lifecycle.md.
If anything errors, say plainly what broke, what you tried, and what you need from the operator to get unblocked. Don't hide the mechanics, but don't make the operator manage them unless they choose to.
Note: the launcher (if installed) already runs claude --continue on every non-first launch,
so the warm resume is handled outside the kernel. The kernel just needs to know that "first
message of a fresh install" means run /start, not greet as the AIgent.
What This Is
aigent-OS is an AI Operating System — a structured framework that defines how an AI agent operates as a strategic advisor and operator. The kernel is 16 numbered documents (00–15) plus a handful of extended specs in system/ that together form a complete system prompt and operational manual.
Architecture
The system is organized as a layered agent hierarchy:
Principal (You)
└── the AIgent (Top-layer operator: strategy, prioritization, delegation)
└── Engineering Agent (CTO / technical execution, receives structured briefs)
└── Sub-agents (Planner, Critic, Finance Agent, Research Agent,
Operations Agent, Communications Writer, Systems Auditor, Scheduler)
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.
- 4d ago First seen · 277 lines · 4,483 tokens per session scan A 473efa563572
aigent-os CLAUDE.md is an instructions file published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed yesterday), licensed MIT. It adds 4,483 tokens to every session, about $0.0224 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 2026-09-01.
Other instructions, from other repositories
ContextLattice AGENTS.md
Instructions for sheawinkler/ContextLattice, covering agent instructions, start, work loop, hooks and host lifecycle safety.
agents-of-the-alley CLAUDE.md
Instructions for PenguinAlleyApps/agents-of-the-alley, covering architecture, agents, non-negotiable rules, quick commands for claude code sessions and philosophy (from pa·co).
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
apm python.instructions.md
Python development guidelines.
GPT-RAG release.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.
autopus-adk GEMINI.md
Gemini CLI instructions for Insajin/autopus-adk, covering autopus-adk harness, 스킬 디렉터리, core guidelines, subagent delegation and file size limit.