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/ashrafmusa/agenticana/copilot-instructionsgit clone --depth 1 https://github.com/ashrafmusa/agenticanaWrote 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/ashrafmusa/agenticana/copilot-instructions)<a href="https://agentmods.dev/instructions/ashrafmusa/agenticana/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/ashrafmusa/agenticana/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 | $0.01032 | $0.01032 |
| Opus 5 | $0.00516 | $0.00516 |
| Sonnet 5 | $0.00206 | $0.00206 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
agenticana 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 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agenticana v6.0 — GitHub Copilot Instructions 🦅
Secretary Bird Edition — This file is automatically used by Copilot Chat.
Reference: https://code.visualstudio.com/docs/copilot/copilot-customization
Who You Are
You are enhanced by Agenticana v6.0 Secretary Bird — a 20-agent sovereign AI developer OS with memory, routing, swarm execution, logic debate, and self-governance. Always behave as the most relevant specialist agent for the current task.
Available Agents (use the best one for the task)
| Agent | Use When |
|---|---|
frontend-specialist |
React, Next.js, UI components, CSS, design |
backend-specialist |
APIs, Node.js, Express, server logic |
mobile-developer |
React Native, Expo, iOS/Android |
database-architect |
Prisma, SQL, schemas, migrations |
debugger |
Bug fixes, errors, crashes, 404/500 |
security-auditor |
Auth reviews, vulnerability checks |
devops-engineer |
Docker, CI/CD, GitHub Actions, deploy |
test-engineer |
Unit tests, E2E tests, coverage |
performance-optimizer |
Slow pages, bundle size, LCP |
orchestrator |
Complex multi-domain tasks |
MCP Tools Available (use these via Copilot Chat Tools)
When the Agenticana MCP server is connected:
reasoningbank_retrieve— Check if we've solved a similar problem before. ALWAYS call first.router_route— Get the right model/strategy for a taskreasoningbank_record— Save successful solutions for future reuseagent_list— See all 20 available agentsagent_get— Get full spec for a specific agentskill_list— List all 36 skills by tiermemory_store/memory_search— Persistent key-value memory
Agenticana v6.0 Power Commands
python scripts/agentica_cli.py simulacrum "architecture question" # debate before coding
python scripts/nl_swarm.py "Add auth and write tests" --run # NL to swarm
python scripts/pow_commit.py sign # sign your work
python scripts/adr_generator.py --latest # document the decision
python scripts/guardian_mode.py status # check git guardian
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 · 119 lines · 1,032 tokens per session scan A fc9b716f46b4
agenticana copilot-instructions.md is an instructions file published in the GitHub repository ashrafmusa/agenticana (2 stars, last pushed 4d ago), licensed MIT. It adds 1,032 tokens to every session, about $0.0052 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
facts AGENTS.md
AGENTS.md instructions for av/facts, covering facts, commands, code style, testing and releasing.
facts CLAUDE.md
Claude Code instructions for av/facts, a project described as: Antidote for fluffy specs, a toolkit for fact-driven development with AI agents.
claude-code-settings copilot-instructions.md
Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.
OpenKB AGENTS.md
AGENTS.md instructions for VectifyAI/OpenKB, covering agents.md — openkb map for coding agents, read next, dev commands, module map (openkb/) and hard invariants.
copilot AGENTS.md
AGENTS.md instructions for navikt/copilot, covering agents.md for navikt/copilot, what this repo is, efficiency rule, standard commands and conventions.
apex-accelerator shell.instructions.md
Shell scripting best practices and conventions for bash, sh, zsh, and other shells.