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.
/plugin marketplace add Everyone-Needs-A-Copilot/claude-copilotnpx agentmods add plugins/everyone-needs-a-copilot/claude-copilot/claude-copilotgit 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.svg" alt="Measured on agentmods" 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 today.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "claude-copilot",
"version": "5.8.0",
"description": "Claude Copilot — 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 — only the path-reference style differs between the two wiring mechanisms.",
"override_layer": "This plugin ships the BASE agents only (the floor). The What it installs
The manifest is a name and a version. 72 skills, 17 commands, 17 agents, 4 hooks travel with it, and installing the plugin installs all of them — 5,372 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 motion-choreography A 95 tokens
- Skill system-design-patterns A 94 tokens
- Skill api-docs A 91 tokens
- Skill git-workflows A 86 tokens
- Skill javascript-patterns A 108 tokens
- Skill kubernetes A 98 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 web-security A 111 tokens
- Skill call-summary A 65 tokens
- Skill ci-cd-patterns A 102 tokens
- Skill crypto-patterns A 119 tokens
- Skill design-patterns A 93 tokens
- Skill pipeline-review A 58 tokens
- Skill protocol A 56 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 frontmatter-validation A 57 tokens
- Skill link-validation A 56 tokens
- Skill litmus-test A 87 tokens
- Skill qa A 44 tokens
- Skill task-copilot A 40 tokens
- Skill token-budget-check A 55 tokens
- Skill orchestrate A 42 tokens
- Skill aesthetic-directions A 102 tokens
- Skill design-heuristics A 95 tokens
- Skill color-palettes A 107 tokens
- Skill uids A 40 tokens
- Skill uxd A 50 tokens
- Skill ta A 44 tokens
- Skill ind A 54 tokens
- Skill me A 39 tokens
- Skill sd A 51 tokens
- Skill doc A 22 tokens
- Skill uid A 37 tokens
- Skill update-project A 35 tokens
- Skill do A 22 tokens
- Skill protocol-router A 35 tokens
- Skill sec A 25 tokens
- Skill launcher A 47 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 memory A 32 tokens
- Skill pause A 31 tokens
- Skill setup-knowledge-sync A 30 tokens
- Skill update-copilot A 43 tokens
- Skill config A 34 tokens
- Skill continue A 37 tokens
- Skill map A 31 tokens
- Skill setup A 31 tokens
- Skill setup-copilot A 41 tokens
- Skill docker-patterns B 85 tokens
- Skill reflect A 32 tokens
- Skill skills-approve A 40 tokens
- Skill forecast A 61 tokens
- Skill create-an-asset A 48 tokens
- Skill competitive-intelligence A 66 tokens
- Skill account-research A 71 tokens
- Skill call-prep A 82 tokens
- Skill draft-outreach A 52 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 memory A 0 tokens
- Command orchestrate A 15 tokens
- Command pause A 0 tokens
- Command setup-knowledge-sync A 0 tokens
- Command update-copilot A 0 tokens
- Command map A 0 tokens
- Command reflect A 0 tokens
- Command knowledge-copilot A 0 tokens
- Command skills-approve A 0 tokens
- Command setup-copilot A 24 tokens
- Command setup-project B 0 tokens
- Command update-project B 0 tokens
- Agent uids A 27 tokens
- Agent uxd A 29 tokens
- Agent ind A 50 tokens
- Agent sd A 26 tokens
- Agent cpa A 43 tokens
- Agent qa A 26 tokens
- Agent ta A 25 tokens
- Agent cco A 26 tokens
- Agent cs A 35 tokens
- Agent cw A 28 tokens
- Agent do A 28 tokens
- Agent kc A 16 tokens
- Agent me A 26 tokens
- Agent sec A 35 tokens
- Agent doc A 26 tokens
- Agent sample-agent A 27 tokens
- Agent uid A 29 tokens
- 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.
- today First seen · 69 lines scan A 40aa5f4b2f35
claude-copilot is a plugin published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed today), 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
knowledge-and-memory
Research methodology, corpus search, persistent memory, iterative workflows, and project knowledge management.
@tekmidian/pai
Personal AI Infrastructure — persistent memory, session continuity, and knowledge graph for Claude Code.
tree-ring-memory
Local-first memory lifecycle, project bootstrap, and receipt-backed harness guidance for Claude Code using Tree Ring Memory v0.15+.
vault-template
Personal Knowledge Management system for Obsidian with AI-powered workflows, goal tracking, and productivity coaching.
compact-manager
Warns the main session as its own context fills, captures a wake packet before compaction, and reorients the session after it — so an autonomous orchestrator survives past one context window.
claude-bestpractice
Enforcement, memory and parallel-session coordination for solo founders running several Claude Code sessions on one repository.