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/vb-nattamai/agent-ready/copilot-instructionsgit clone --depth 1 https://github.com/vb-nattamai/agent-readyWrote 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/vb-nattamai/agent-ready/copilot-instructions)<a href="https://agentmods.dev/instructions/vb-nattamai/agent-ready/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/vb-nattamai/agent-ready/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 | $0.00578 | $0.00578 |
| Opus 5 | $0.00289 | $0.00289 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
agent-ready 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions — hello_world
Project Summary
A minimal Flask REST API (Python ≥ 3.11) that serves personalised greetings, records them in an in-memory list, and exposes health-check and listing endpoints. All logic lives in a single module (app.py). No database or external services are involved.
Commands
| Action | Command |
|---|---|
| Install | pip install -r requirements.txt |
| Install (editable/dev) | detected as likely: pip install -e . — verify before use |
| Run | python app.py |
| Test | pytest |
Module Layout
app.py — Flask app object, all four REST endpoints, in-memory greetings list
tests/
test_app.py — pytest tests for all API endpoints via Flask test client
Restricted Paths
Restricted write paths: Not determinable from source — fill in agent-context.json static.restricted_write_paths after reviewing your repo.
Never do without updating tests:
- Rename or remove any public endpoint:
/,/health,/greet/<name>,/greetings - Rename the Flask variable
appinapp.py— tests import it directly - Introduce a database dependency without migration/setup instructions
Key Domain Concepts
| Term | Definition |
|---|---|
| Greeting | A recorded personalised message containing a user's name and a hello message, stored in the in-memory list. |
| Health Check | A lightweight endpoint (/health) that returns an ok status to confirm the service is running. |
| Service Root | The index endpoint (/) that returns the service name and version metadata. |
Top 3 Pitfalls
- Stale in-memory state in tests —
_greetingsis a module-level list that persists across requests within a process. Tests that do not reset the list between runs will see data from previous tests, causing false failures or false passes.
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 · 58 lines · 578 tokens per session scan A 3d19d89813c1
agent-ready copilot-instructions.md is an instructions file published in the GitHub repository vb-nattamai/agent-ready (5 stars, last pushed 1mo ago), licensed MIT. It adds 578 tokens to every session, about $0.0029 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
HarnessSmith AGENTS.md
Instructions for EpisodeYu/HarnessSmith, covering agents.md — harnesssmith 快速上手, 1. 这是什么（一句话）, 2. 两层心智（最重要，先记住）, 3. 仓库地图 and 4. 常用命令（已验证）.
apm python.instructions.md
Python development guidelines.
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
foundry-local python-cffi-pointer-types.instructions.md
Use when working on the Python SDK's native bindings (cffi), especially when defining new Item subclasses, working with flItemQueue, or extending Request/Session methods that pass native handles.
ConsultMe CLAUDE.md
Claude Code instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.
pydantic-ai-gepa AGENTS.md
AGENTS.md instructions for indexedlabs/pydantic-ai-gepa, covering repository guidelines, mighty workflow, project structure & module organization, build, test, and development commands and coding style & naming conventions.