ai-agents copilot-instructions.md

ai-agents copilot-instructions.md is an instructions file for GitHub Copilot from rjmurillo/ai-agents. It costs 1,113 tokens per session, scanned A, original, MIT.

GitHub Copilot instructions for working in the ai-agents repository. They define the main references, agent delegation rules, and required setup for the Serena MCP tool.

In plain words
What is it for?
Use them when asking Copilot to handle multi-step work, explore a codebase, implement changes, review plans, or perform security checks.
Why use it?
They help Copilot follow repository-specific behavior and route complex tasks to the right specialist agent.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/rjmurillo/ai-agents/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for ai-agents copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/copilot-instructions.svg)](https://agentmods.dev/instructions/rjmurillo/ai-agents/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,113 This file is loaded in full into every session.
When invoked 1,113 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01113 $0.01113
Opus 5 $0.00557 $0.00557
Sonnet 5 $0.00223 $0.00223
Haiku 4.5 $0.00111 $0.00111

Measured yesterday against content hash f0e44ddeda20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-agents 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 yesterday.

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.

.github/copilot-instructions.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Instructions

IMPORTANT: File minimal. Cut context bloat. Detail in AGENTS.md.

Global Behavioral Steering

For cross-harness behavior rules, local Copilot sessions can also read ~/.copilot/copilot-instructions.md. AGENTS.md remains this repository's primary reference for ai-agents-specific rules.

Copilot Cloud cannot read local dotfiles. If you have access to Richard's dotfiles repo, use the branch-agnostic fallback link in Key Documents.

Agent Delegation for Complex Tasks

Multi-step tasks, specialized expertise, big context → prefer delegation via #runSubagent rather than inline handling.

When to Delegate Agent Example Prompt
Multi-step coordination orchestrator "Implement OAuth 2.0 with tests and docs"
Codebase exploration analyst "Investigate why cache invalidation fails"
Architecture decisions architect "Design the event sourcing pattern for orders"
Implementation work implementer "Implement the UserService per approved plan"
Plan validation critic "Review the migration plan for gaps"
Security review security "Assess auth flow for vulnerabilities"

Why delegate:

  • Context window efficient (agent start fresh)
  • Specialized prompts + constraints
  • Focused results to synthesize

Delegation pattern:

#runSubagent orchestrator "Help me implement feature X end-to-end"

Keep inline: Simple single-file edits, quick lookups. No specialized reasoning needed.

Primary Reference

Read AGENTS.md FIRST for full instructions:

  • Session protocol (blocking gates)
  • Agent catalog + workflows
  • Directory structure
  • GitHub workflow requirements
  • Skill system
  • Memory management
  • Quality gates

Path: ../AGENTS.md (repo root)

Before changing hooks, hook generators, agents, skills, instructions, rules, or runtime scripts shared by Claude Code and Copilot CLI, load agent-harness-reference. Execute contract changes through ai-agents-portability-campaign. Do not infer one harness from another.

Read the full file on GitHub · 125 lines

Changes

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.

  1. yesterday First seen · 125 lines · 1,113 tokens per session scan A f0e44ddeda20

Subscribe to this mod's changes

ai-agents copilot-instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 1,113 tokens to every session, about $0.0056 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 2026-09-03.