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.
git clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilotWrote 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/plugins/everyone-needs-a-copilot/claude-copilot/claude-copilot)<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.
<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>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.
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 — 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)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.
- Skill jest-patterns A 120 tokens
- Skill pytest-patterns A 129 tokens
- Skill protocol A 56 tokens
- Skill qa A 44 tokens
- Skill api-docs A 91 tokens
- Skill javascript-patterns A 108 tokens
- Skill motion-choreography A 95 tokens
- Skill premium-interaction-craft A 92 tokens
- Skill react-patterns A 102 tokens
- Skill refactoring-patterns A 111 tokens
- Skill spatial-luminous-design A 100 tokens
- Skill system-design-patterns A 94 tokens
- Skill ci-cd-patterns A 102 tokens
- Skill crypto-patterns A 119 tokens
- Skill git-workflows A 86 tokens
- Skill kubernetes A 98 tokens
- Skill pipeline-review A 58 tokens
- Skill python-idioms A 116 tokens
- Skill stride-dread A 145 tokens
- Skill threat-modeling A 123 tokens
- Skill tutorial-patterns A 61 tokens
- Skill typography-pairings A 98 tokens
- Skill ux-patterns A 99 tokens
- Skill voice-tone A 100 tokens
- Skill web-security A 111 tokens
- Skill call-summary A 65 tokens
- Skill design-patterns A 93 tokens
- Skill frontmatter-validation A 57 tokens
- Skill link-validation A 56 tokens
- Skill task-copilot A 40 tokens
- Skill litmus-test A 87 tokens
- Skill token-budget-check A 55 tokens
- Skill orchestrate A 42 tokens
- Skill cleanup A 35 tokens
- Skill aesthetic-directions A 102 tokens
- Skill design-heuristics A 95 tokens
- Skill ta A 44 tokens
- Skill color-palettes A 107 tokens
- Skill me A 39 tokens
- Skill uids A 40 tokens
- Skill uxd A 50 tokens
- Skill sd A 51 tokens
- Skill uid A 37 tokens
- Skill ind A 54 tokens
- Skill do A 22 tokens
- Skill doc A 22 tokens
- Skill protocol-router A 35 tokens
- Skill reflect A 32 tokens
- Skill update-project A 35 tokens
- Skill sec A 25 tokens
- Skill setup-project A 34 tokens
- Skill specialist-agents A 50 tokens
- Skill extensions A 35 tokens
- Skill knowledge-copilot A 39 tokens
- Skill launcher A 47 tokens
- Skill memory A 32 tokens
- Skill setup-knowledge-sync A 30 tokens
- Skill config A 34 tokens
- Skill continue A 37 tokens
- Skill map A 31 tokens
- Skill pause A 31 tokens
- Skill setup A 31 tokens
- Skill setup-copilot A 41 tokens
- Skill skills-approve A 40 tokens
- Skill update-copilot A 43 tokens
- Skill docker-patterns B 85 tokens
- Skill forecast A 61 tokens
- Skill create-an-asset A 48 tokens
- Skill competitive-intelligence A 66 tokens
- Skill draft-outreach A 52 tokens
- Skill account-research A 71 tokens
- Skill call-prep A 82 tokens
- Skill daily-briefing A 68 tokens
- Command protocol A 0 tokens
- Command continue A 0 tokens
- Command config A 0 tokens
- Command setup A 0 tokens
- Command extensions A 0 tokens
- Command orchestrate A 15 tokens
- Command pause A 0 tokens
- Command update-copilot A 0 tokens
- Command map A 0 tokens
- Command memory A 0 tokens
- Command reflect A 0 tokens
- Command setup-knowledge-sync A 0 tokens
- Command knowledge-copilot A 0 tokens
- Command skills-approve A 0 tokens
- Command setup-copilot A 24 tokens
- Command cleanup A 0 tokens
- Command setup-project B 0 tokens
- Command update-project B 0 tokens
- Agent uids A 27 tokens
- Agent uxd A 29 tokens
- Agent qa A 26 tokens
- Agent sd A 26 tokens
- Agent ind A 50 tokens
- Agent me A 26 tokens
- Agent ta A 25 tokens
- Agent cpa A 43 tokens
- Agent cw A 28 tokens
- Agent sec A 35 tokens
- Agent cco A 26 tokens
- Agent cs A 35 tokens
- Agent do A 28 tokens
- Agent doc A 26 tokens
- Agent kc A 16 tokens
- Agent uid A 29 tokens
- Hook PostToolUse A not measured
- Hook SubagentStart A not measured
- Hook SubagentStop A not measured
- Hook PreToolUse A not measured
- Hook SessionStart A not measured
- Hook UserPromptSubmit A not measured
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.
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.
- yesterday Changed 98c3faa78e40
- 3d ago Changed 79e2776a705f
- 4d ago Changed cb43fe1365b0
- 6d ago Changed 93923aef024c
- 7d ago Changed · -5 lines dbe012cfcf1a
- 12d ago Changed 392105592d51
- 13d ago Changed 7b581043b977
- 15d ago Changed 67c122760f18
- 27d ago Changed b440d5eaa68a
- 1mo ago First seen · 69 lines scan A 9e344b1b20d1
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.
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.
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.
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.
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…
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…
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.