claude-copilot

claude-copilot is a plugin for Claude Code from Everyone-Needs-A-Copilot/claude-copilot. Its manifest loads nothing; the 73 skills, 18 commands, 16 agents, 6 hooks it bundles cost 5,380 tokens per session together, scanned A, original, MIT.

A framework for Claude with specialised agents, reusable skills, commands, and automatic checks. Its agents cover architecture, engineering, quality assurance, service design, DevOps, documentation, and onboarding, while it also provides persistent memory and task tracking.

In plain words
What is it for?
Use it to organise architecture and engineering work, quality checks, DevOps tasks, documentation, service design, and bringing new contributors up to speed.
Why use it?
It gives different software tasks defined roles and keeps project context and work tracking available across sessions.

Plugin for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions subagents.

Good fit Use it to organise architecture and engineering work, quality checks, DevOps tasks, documentation, service design, and bringing new contributors up to speed.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add Everyone-Needs-A-Copilot/claude-copilot
/plugin install claude-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.

Clone the repo
git clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilot

Made for: Claude Code.

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 claude-copilot

README.md
[![agentmods](https://agentmods.dev/badge/plugins/everyone-needs-a-copilot/claude-copilot/claude-copilot/github.svg)](https://agentmods.dev/plugins/everyone-needs-a-copilot/claude-copilot/claude-copilot)
Your own site
<a href="https://agentmods.dev/plugins/everyone-needs-a-copilot/claude-copilot/claude-copilot"><img src="https://agentmods.dev/badge/plugins/everyone-needs-a-copilot/claude-copilot/claude-copilot/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-copilot

Your own site · 80×15
<a href="https://agentmods.dev/plugins/everyone-needs-a-copilot/claude-copilot/claude-copilot"><img src="https://agentmods.dev/badge/plugins/everyone-needs-a-copilot/claude-copilot/claude-copilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 73 skills, 18 commands, 16 agents, 6 hooks cost 5,380 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

claude-copilot 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.

The scan reads plugin.json. This mod also ships 1 executable file (check-manifest.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude-plugin/plugin.json · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "claude-copilot",
  "version": "5.24.0",
  "description": "Claude Copilot \u2014 a framework of specialized agents, skills, commands, and hooks that give Claude persistent memory, expert methodology, and task tracking. Agents cover architecture (ta), engineering (me), QA (qa), service design (sd), DevOps (do), documentation (doc), and knowledge onboarding (kc).",
  "author": "Claude Copilot contributors",
  "homepage": "https://github.com/pabloalej/claude-copilot",
  "license": "MIT",
  "claude_plugin_spec": "1.0",
  "agents": "../.claude/agents",
  "skills": "../.claude/skills",
  "commands": "../.claude/commands",
  "hooks": {
    "SessionStart": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "${CLAUDE_PLUGIN_ROOT}/../.claude/hooks/session-start.sh"
          }
        ]
      }
    ],
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "${CLAUDE_PLUGIN_ROOT}/../.claude/hooks/pretool-check.sh"
          }
        ]
      }
    ],
    "SubagentStop": [
      {
        "matcher": "me|qa",
        "hooks": [
          {
            "type": "command",
            "command": "${CLAUDE_PLUGIN_ROOT}/../.claude/hooks/subagent-stop.sh"
          }
        ]
      }
    ],
    "UserPromptSubmit": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "${CLAUDE_PLUGIN_ROOT}/../.claude/hooks/user-prompt-submit.sh"
          }
        ]
      }
    ]
  },
  "_notes": {
    "hook_portability": "Hooks reference the same scripts in .claude/hooks/ whether installed as a plugin (${CLAUDE_PLUGIN_ROOT} resolves to the plugin install dir) or as a direct clone (settings.json wires the same scripts with absolute paths). No script changes were needed \u2014 only the path-reference style differs between the two wiring mechanisms.",
    "override_layer": "This plugin ships the BASE agents only (the floor)

Read the full file on GitHub · 64 lines

Contents

What it installs

The manifest is a name and a version. 73 skills, 18 commands, 16 agents, 6 hooks travel with it, and installing the plugin installs all of them — 5,380 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

2 files beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 Changed 98c3faa78e40
  2. 3d ago Changed 79e2776a705f
  3. 4d ago Changed cb43fe1365b0
  4. 6d ago Changed 93923aef024c
  5. 7d ago Changed · -5 lines dbe012cfcf1a
  6. 12d ago Changed 392105592d51
  7. 13d ago Changed 7b581043b977
  8. 15d ago Changed 67c122760f18
  9. 27d ago Changed b440d5eaa68a
  10. 1mo ago First seen · 69 lines scan A 9e344b1b20d1

Subscribe to this mod's changes

claude-copilot is a plugin published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (14 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-04.

Related

Other plugins, from other repositories

claude-mem-grok-bot

Persistent memory for Grok Bot. No host hooks: transcript watcher plus MCP. Local worker with host-login observer, or remote cmem.ai. Install without Cursor.

thedotmack/claude-mem · not measured

recall

Durable, fully-local project memory for Claude Code. Logs every session to .recall/history.md and condenses it into .recall/context.md with a local Python summarizer (TF-IDF + TextRank) — no API key, no external model, nothing leaves your machine. New sessions resume from the saved context.

raiyanyahya/recall · not measured

yantrikdb

Cognitive memory for AI agents — semantic recall, a knowledge graph, contradiction detection and procedural learning. Local-first: one SQLite file, no account, no telemetry.

yantrikos/yantrikdb-mcp · not measured

evolving-claude-md

Turn CLAUDE.md into a living Decisions & Learnings log that stays bounded: a format contract enforced at write time by a PreToolUse lint, four downward pressures (strike-through, merge, graduation, quarterly archive), staleness detection against the tree, and a tree-grounded coverage check for the essentials a file…

alexmond/alexmskills · not measured

memory-kit

Persistent memory for Claude Code agents: a hot cache injected every session and held under three size caps, per-session handoffs, and agent-audited promotion into knowledge articles and rules. Carries the builder's layers too — executor/recon/idea-validator agents, session review, second opinion, agent QA and a…

awrshift/claude-memory-kit · not measured

codies-memory

File-based two-tier memory system for AI agents. Agent-namespaced vaults with promotion pipelines, trust levels, CLI write commands, and explicit general read mode for vault-less notes. Gives any agent persistent memory across sessions.

pyros-projects/limitless · not measured