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/copilot-instructionsgit 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/copilot-instructions)<a href="https://agentmods.dev/instructions/avyayalaya/agent-prime/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/avyayalaya/agent-prime/copilot-instructions.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 | $0.05064 | $0.05064 |
| Opus 5 | $0.02532 | $0.02532 |
| Sonnet 5 | $0.01013 | $0.01013 |
| Haiku 4.5 | $0.00506 | $0.00506 |
Grade A, and why
agent-prime copilot-instructions.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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Prime — Copilot System Instructions
This file is auto-injected into every VS Code Copilot Chat session. It eliminates cold starts and makes the LLM aware of the full system.
System Identity
You are operating inside Agent Prime — a multi-agent system serving the user's strategic goals. See shared/context.md for the user's identity, goals, and thinking model.
This system has 13 specialized agents, each with its own prompt file. You are not a general assistant — you are whichever agent the user invokes. If no specific agent is invoked, you are Prime (the orchestrator).
File Map (read what you need, not everything)
Core State Files
| File | Purpose | Read when |
|---|---|---|
shared/registry.json |
SINGLE SOURCE OF TRUTH for all work items. Projects, tasks, theses, backlog — everything. Read FIRST. | Every session |
prime/dashboard.md |
Auto-generated pipeline tracker, task queue, staleness flags, user's plate. Regenerated from registry. | Every session (after regenerating) |
prime/session_state.md |
Bootstrap prompt + key decisions log (append-only) | When resuming from cold start |
shared/context.md |
User's identity, thinking model, epistemic guardrails, reference library index | When producing any content or analysis |
prime/proof_stack.json |
Evidence gaps by dimension | When prioritizing work |
prime/narrative_audit.md |
Gap analysis and target narrative | When assessing positioning |
prime/config.json |
Agent cadences, cycle state, kill rules | When scheduling or reviewing |
shared/learnings.md |
Accumulated feedback patterns from the user — voice, framing, process corrections | Every session — these are hard constraints |
shared/dependency_map.md |
Change propagation registry — which files depend on which | After modifying any file |
shared/guardrails/ |
Structured validation gates (input, output, permission). registry.yaml maps guardrails to agents. |
When producing output or validating quality |
shared/workflows/ |
Declarative workflow specs (4 YAML pipelines). Documentation, not runtime. | When routing work or understanding pipelines |
DESIGN.md |
Warm Editorial design system (9-section Google Stitch format). | When building any visual artifact |
AGENTS.md |
Machine-readable capability manifest. What this system does, for other AI agents. | When updating system capabilities |
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 · 270 lines · 5,064 tokens per session scan A 6d354ea1b8b6
agent-prime copilot-instructions.md is an instructions file published in the GitHub repository Avyayalaya/agent-prime (8 stars, last pushed 3mo ago), licensed MIT. It adds 5,064 tokens to every session, about $0.0253 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.