everything-copilot-cli AGENTS.md

A project guide describing the agents in the everything-copilot-cli system. It lists roles such as planning, architecture, code review, security review, test-driven development, build-error fixing, documentation, and cleanup.

In plain words
What is it for?
Use it when planning work in everything-copilot-cli or deciding which agent should handle a particular software task.
Why use it?
It helps an agent choose the right specialist and understand each agent’s responsibilities and escalation paths.

Instructions file for CodexOpenCode

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/drvoss/everything-copilot-cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/drvoss/everything-copilot-cli

Made for: Codex, OpenCode.

Per session 3,850 This file is loaded in full into every session.
When invoked 3,850 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 $0.03850 $0.03850
Opus 5 $0.01925 $0.01925
Sonnet 5 $0.00770 $0.00770
Haiku 4.5 $0.00385 $0.00385

Measured yesterday against content hash cff995fa6e3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

everything-copilot-cli 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 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.

AGENTS.md · 466 lines

How it starts

The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents Directory

Catalog of all core agents in the everything-copilot-cli system. Each agent maps to a Copilot CLI agent type and has defined responsibilities, tools, and escalation paths.


Agent Summary

# Agent Purpose Copilot Agent Type Model
1 planner Break down complex features, identify dependencies general-purpose claude-sonnet-4.6
2 architect System design, scalability decisions general-purpose claude-sonnet-4.6
3 code-reviewer Quality, maintainability, best practices code-review claude-sonnet-4.6
4 security-reviewer Vulnerability detection, hardened defaults code-review claude-sonnet-4.6
5 tdd-guide Test-driven development workflow general-purpose gpt-5-mini
6 build-error-resolver Fix build/compilation errors task gpt-5-mini
7 doc-updater Documentation sync general-purpose claude-haiku-4.5
8 refactor-cleaner Dead code removal, cleanup general-purpose gpt-5-mini

1. Planner

Purpose: Break down complex features into implementable tasks, identify dependencies between work items, and create structured execution plans.

When to Use

  • A feature request spans multiple files, modules, or systems
  • The task requires sequencing — some work must happen before other work
  • You need a todo list with dependencies before starting implementation
  • The user invokes Plan Mode or asks for a breakdown

Agent Type Mapping

  • Copilot agent type: general-purpose
  • Copilot mode: Plan Mode (creates plan.md, uses exit_plan_mode for approval)
  • Fleet compatible: Yes — planner creates the plan, fleet agents execute it

Tool Permissions

Tool Access Notes
grep ✅ Full Search codebase for dependencies
glob ✅ Full Discover file structure
view ✅ Full Read existing code and configs
edit ❌ None Planner does not modify code
create ✅ Limited Only for plan.md
sql ✅ Full Todo tracking with dependencies
powershell ⚠️ Read-only Inspect build state, test results

Read the full file on GitHub · 466 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 · 466 lines · 3,850 tokens per session scan A cff995fa6e3a

Subscribe to this mod's changes

everything-copilot-cli AGENTS.md is an instructions file published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 5d ago), licensed MIT. It adds 3,850 tokens to every session, about $0.0192 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 2026-08-30.

Related

Other instructions, from other repositories