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/avyayalaya/agent-prime/agents-mdgit clone --depth 1 https://github.com/Avyayalaya/agent-primeWrote 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/avyayalaya/agent-prime/agents-md)<a href="https://agentmods.dev/instructions/avyayalaya/agent-prime/agents-md"><img src="https://agentmods.dev/badge/instructions/avyayalaya/agent-prime/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 | $0.03895 | $0.03895 |
| Opus 5 | $0.01947 | $0.01947 |
| Sonnet 5 | $0.00779 | $0.00779 |
| Haiku 4.5 | $0.00390 | $0.00390 |
Grade A, and why
agent-prime 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Agent Prime
Machine-readable system manifest. Primary audience: AI orchestrators deciding whether to route work here.
Overview
Agent Prime is an open-source AI operating system built entirely from markdown files. It provides 13 specialized agents + a runtime-portable 5-agent quality gate (Agent Council), 12 domain skills with typed schemas, persistent memory with recursive self-improvement, 8 structured guardrails, and 4 declarative workflows. Zero dependencies — no database, no runtime, no package manager. Clone the repo and point any LLM at it. The system gets permanently smarter with every correction via an append-only learnings registry that propagates constraints to all agents.
Repository: https://github.com/avyayalaya/agent-prime
Instruction files: CLAUDE.md (Claude Code), .github/copilot-instructions.md (GitHub Copilot), both kept in sync.
Architecture: Markdown-only, 7 layers, cross-LLM compatible (Claude Code, GitHub Copilot, Gemini CLI).
Capabilities
- 13 specialized agents with typed inputs, outputs, and Context Verification Gates
- 12 PM-domain skills with codified methodologies, failure modes, and benchmark scores
- Recursive learning loop: Every user correction becomes a permanent rule in
shared/learnings.md, applied to all agents in all future sessions - 8 structured guardrails enforced via system rules in
CLAUDE.md(including a runtime-portable 5-agent quality gate) - 4 declarative workflows composing agents into end-to-end pipelines
- 49 system rules governing context verification, voice, NDA compliance, change propagation, and quality
- 100+ accumulated learnings across voice, content, process, quality, build, and agent design categories
- Session resilience: Write-ahead journaling, crash recovery, session audit, learning extraction
- Cross-LLM compatibility: Works on Claude Code, GitHub Copilot Chat, Gemini CLI without modification
- Onboarding wizard: Interactive setup in under 10 minutes via the Onboarder agent
- Zero dependencies: No npm, no pip, no Docker. Python 3.10+ for optional scripts only.
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 · 244 lines · 3,895 tokens per session scan A 2af47bd5bd75
agent-prime AGENTS.md is an instructions file published in the GitHub repository Avyayalaya/agent-prime (8 stars, last pushed 3mo ago), licensed MIT. It adds 3,895 tokens to every session, about $0.0195 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
solo AGENTS.md
AGENTS.md instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.
research-os AGENTS.md
Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).
AI-System-Design-Consultant CLAUDE.md
Claude Code instructions for deepanshu2711/AI-System-Design-Consultant, covering claude.md, what this is, running it, load-bearing typos — do not "fix" these paths and agent node pattern.
agent-eve CLAUDE.md
Instructions for shehryarsaroya/agent-eve, covering claude.md — agent eve (né the compact, then agent transfer), 0. 🚨 hard rules, 1. what this is, 2. doc map and 3. state of play (2026-07-26).
team-shinchan AGENTS.md
Instructions for seokan-jeong/team-shinchan, covering agents.md - team-shinchan agent map, layer architecture, agent registry, call flow and quick reference.
coordinate-agents AGENTS.md
AGENTS.md instructions for hogancv/coordinate-agents, covering repository instructions for ai contributors, canonical identity, repository map, required checks and change rules.