The agent profile manager for AI coding agents.
Your agent walks into a directory. The cuecard tells it who to be.
npm install -g cue-ai
A cuecard is everything your AI coding agent needs to be useful in one directory — the skills it loads, the MCP servers it connects to, the plugins it boots with, the persona it adopts, the playbooks it follows, the quality gates that block its "done" claim.
One cuecard per project. Your agent reads the right one the moment you launch.
| layer | what's on the cuecard |
|---|---|
| skills | only the ones this project actually needs |
| MCPs | scoped per directory, no global sprawl |
| plugins | the Claude Code plugins this project wants — no more |
| persona | how the agent thinks, writes, and self-edits |
| playbooks | the steps the agent follows for known tasks |
| gates | what must pass before the agent says "done" |
npm install -g cue-ai # 1. install
cue discover search "code review" # 2. find a skill
cue discover install review/code-review # 3. add it
claude # 4. launch — the cuecard is loadedSearch. Install. Use. No config files to edit. Works the same with codex, cursor, cline, gemini, and five other agents.
One cuecard. Ten supported agents.
10–25× token cost reduction
< 5 ms warm launch overhead
69 pre-built cuecards · 110+ local skills
10 AI coding agents supported
MIT open source · zero telemetry · no daemon
Loading everything costs you tokens on every single message. cuecards cut context size by 10–25×.
| Scenario | Context loaded | Cost per session (Sonnet) |
|---|---|---|
| Without cuecards — all skills + every MCP | ~180k tokens | ~$2.70 😱 |
With cuecards — backend profile |
~8k tokens | ~$0.12 ✅ |
With cuecards — caveman-quick |
~2k tokens | ~$0.03 🚀 |
That's 22× fewer tokens on a real backend loadout vs the unmanaged baseline. Your model picks the right tool faster because it's not scanning irrelevant descriptions on every message.
cue cost # token budget for your active profile
cue cost --profile full # compare against the "everything" baseline- Cut per-message token cost 10–25×. Skills, MCPs, and plugins scoped per directory, not globally loaded into every session.
- Five-dimensional agents. Persona + playbooks + quality gates + evals + failure loop. Not just "more tools loaded" — composable expertise.
- One cuecard, ten agents. The same
profile.yamlmaterializes into Claude Code, Codex, Cursor, Cline, Gemini, Copilot, Windsurf, Roo, Amp, and Aider native formats.
Other wins
- Discover real skills, not awesome-lists.
cue discover searchqueries GitHub Code Search forfilename:SKILL.md, scores results, maps each repo to a cuecard. - Install every CLI the cuecard needs in one command.
cue cli install --all <cuecard>auto-detects apt / brew / snap / pipx / npm per OS. - Block "done" claims with quality gates. Stop-hook validators auto-run tests, lint, and build before the agent can declare a task complete.
- Open safe, meaningful PRs on skill repos. Built-in 90-day per-repo cooldown, 25-PRs/day cap, and
<!-- cue: ignore -->opt-out marker. - Failure-feedback loop.
cue failures --proposereads recent session failures and asks Claude to draft profile improvements.
cuecards-managed agents tag every research- or decision-relevant claim with a colored confidence marker so you can scan trust at a glance:
| Tier | Tag | Meaning |
|---|---|---|
| 🟢 Green | [VERIFIED] / [KNOWN] |
Trust it (~90–99%) |
| 🟡 Yellow | [INFERRED] / [ASSUMED] |
Verify if stakes matter (~50–85%) |
| 🟠 Orange | [GUESSED] / [STALE] |
Verify before acting (~20–45%) |
| 🔴 Red | [UNKNOWN] |
Don't trust; agent refused to fabricate |
Optional decile calibration on yellow/orange: 🟡 [INFERRED ~80%], 🟠 [GUESSED ~30%]. The ~ signals it's a rough self-estimate, not a true probability.
Full system + when each tag fires: resources/skills/skills/meta/integrity-tags/SKILL.md · Canonical protocol: resources/personas/integrity-protocol.md (auto-injected into every profile via persona_includes).
One repo. 69 pre-built expert agents. Pin one with
cue use <name>andclaudelaunches with that cuecard's skills, MCPs, hooks, and commands materialized.
cue list # show everything
cue auto-detect # suggest the right one for cwd
cue use medusa-dev # pin to current directory
claude # launches with that cuecard's loadout| Profile | What it's for |
|---|---|
| 🐢 core | Baseline shared by every cue profile — essentials only |
| 🦄 full | Diagnostic fallback that loads every local skill and MCP |
| Profile | What it's for |
|---|---|
| 🐻 backend | APIs, webhooks, security review, CI, packaging, database, deploy |
| 🐹 go-api | Go API development — net/http, gin/echo/chi, GORM, testing |
| 🐍 python | FastAPI/Django/Flask APIs, SQLAlchemy/Alembic, pytest |
| 🦀 rust | All-in-one Rust — async, web, CLI/TUI, embedded, FFI, WASM, perf |
| Profile | What it's for |
|---|---|
| 🦋 frontend | Frontend UI implementation, redesign, screenshots, testing |
| ▲ nextjs | Next.js full-stack — App Router, Server Components, Vercel |
| ⚡ vite | Vite + React + TanStack ecosystem |
| 🎲 threejs | Three.js 3D — geometry, materials, shaders, animation |
| Profile | What it's for |
|---|---|
| 🔒 cybersecurity | 754 red/blue team skills + agentshield auditor |
| 🦉 research | Source-backed lookup, extraction, browser/market research |
| 🦚 creative-media | Image, video, product asset, brand workflows |
| 🎬 video | Frame extraction, audio transcription, visual understanding |
| 🐝 docs-writer | Documentation, Markdown, PDF, Obsidian, structured writing |
| 🦜 marketing | Copywriting, SEO, CRO, growth, channels, X/Twitter automation |
| 💼 career | Job hunting, resume, interview prep, salary negotiation |
| 🦊 medusa-dev | Medusa v2 backend, storefront, admin, migration |
| 🐺 fleet-control | Multi-agent orchestration, Colony coordination, gx safety |
| 🏢 agency | A full agency on tap — 63 delegatable subagents (design, sales, product, PM, finance, game dev, XR, paid media, QA) |
Full machine-readable list (all 69): docs/data/profiles.md. Don't see a fit? Run cue auto-detect or cue ai "describe your stack" to scaffold a new one.
The same profile.yaml materializes into each agent's native format — .cursorrules, .clinerules, ~/.gemini/skills/*.md, .github/copilot-instructions.md, etc.
cue materialize cursor --profile backend # → .cursorrules + .cursor/mcp.json
cue materialize --all --profile backend # → all 10 agents at onceFull materialization matrix
| Agent | cue materialize command |
Output |
|---|---|---|
| Claude Code | (default — shim) | ~/.config/cue/runtime/<profile>/claude/ |
| OpenAI Codex | (default — shim) | ~/.config/cue/runtime/<profile>/codex/ |
| Cursor | cue materialize cursor |
.cursorrules · .cursor/mcp.json |
| Cline | cue materialize cline |
.clinerules · cline_mcp_settings.json |
| Gemini CLI | cue materialize gemini |
~/.gemini/skills/*.md |
| GitHub Copilot | cue materialize copilot |
.github/copilot-instructions.md |
| Windsurf | cue materialize windsurf |
.windsurfrules · .windsurf/mcp.json |
| Roo Code | cue materialize roo |
.roo/rules/*.md · .roo/mcp.json |
| Sourcegraph Amp | cue materialize amp |
AGENTS.md · .amp/mcp.json |
| Aider | cue materialize aider |
.aider.conventions.md |
# Pick a profile
cue use <profile> # switch profile for this directory
cue list # see all available profiles
# Measure
cue cost # token budget for active profile
cue eval --breakdown # per-message vs on-demand
cue eval --compare a b # side-by-side delta
# System dependencies
cue cli install --all --yes # install every missing CLI
# Quality + discovery
cue lint-skill <path> [--fix] # validate SKILL.md against R001-R008
cue marketplace discover --cli-aware # find skill repos on GitHub
cue failures --propose [profile] # Claude drafts profile improvements
# Audit
cue optimizer # dashboard: skills, MCPs, CLIs, usage per profile
cue doctor --fix # diff declared vs actual state, auto-repaircue --help shows the full ~50-subcommand surface. The set above covers everything you'll touch weekly.
npm install -g cue-aiThen in any project:
cd ~/projects/q4-launch
echo marketing > .cue-profile
claudeOther install paths
| Path | Command |
|---|---|
| One-line script | curl -fsSL https://raw.githubusercontent.com/opencue/claude-code-skills/main/get.sh | bash |
| Manual clone | git clone https://github.com/opencue/claude-code-skills.git ~/Documents/cue && ~/Documents/cue/install.sh |
| Per-OS bootstrap | paste setup/macos.md · setup/linux.md · setup/windows.md into Claude Code |
install.sh --help lists --yes, --codex, --uninstall. Idempotent — safe to re-run.
Does this break Claude Code's auto-update?
No. cue doesn't touch the claude binary — it intercepts the call via a one-line bash shim in ~/.local/bin/claude, sets CLAUDE_CONFIG_DIR, and execs the real binary. Claude Code's update mechanism still runs identically.
Is this a daemon?
No. Pure CLI. When you type claude, the shim runs cue launch, does a sha256 compare, materializes only if anything changed, then execs. Nothing stays resident.
How fast is the overhead?
Cold start: 50–200 ms. Warm start: <5 ms (sha256 compare + exec). Imperceptible next to Claude Code's own startup.
Does cue send telemetry?
No. Everything cue computes (including the per-skill usage bars in cue optimizer) reads from your local ~/.claude/projects/**/*.jsonl transcripts. Nothing leaves the machine.
What's the difference between cue and skillport / Kiro Powers?
| cue | skillport / agent-skills-cli | Kiro Powers | |
|---|---|---|---|
| Skills | ✅ | ✅ | ✅ |
| MCPs | ✅ | — | ✅ |
| Plugins | ✅ | — | — |
| Per-directory profiles | ✅ | — | ◐ (IDE-only) |
| Inheritance | ✅ | — | — |
| Persona / playbooks / gates / evals | ✅ | — | — |
| Multi-agent (Cursor/Cline/Copilot/etc.) | ✅ (10) | Claude only | IDE-only |
| CLI installer | ✅ | — | — |
| Failure-feedback loop | ✅ | — | — |
| Daemon required | None | None | IDE process |
cuecards is the only one that treats agent expertise as a composable system.
What does cue NOT do?
- It does not modify or repackage the Claude Code / Codex binary.
- It does not host a remote skill marketplace — skills live in your repo or come from open-source sources.
- It does not coordinate multi-agent runs (that's
recodeee/colony+gitguardex, layered via the parallel-agents tier).
The bits that didn't fit on the landing page:
| Topic | Read |
|---|---|
| Launch flow (resolve → materialize → exec) | docs/launch.md |
| Profile catalog (all 69, machine-readable) | docs/data/profiles.md |
| Bootstrap contract for AI agents installing cue | AGENTS.md |
| Parallel agents tier (Colony + gitguardex) | setup/parallel-agents.md |
Confidence-tag system ([VERIFIED], [INFERRED], [GUESSED], etc.) |
resources/skills/skills/meta/integrity-tags/SKILL.md |
Topics like the 5-dimensional expert agent model, system CLI installer mechanics, marketplace discovery, SKILL.md linter rules, and the cue optimizer dashboard are tracked in git history at the old README until they get their own pages — git log --diff-filter=D -- README.md finds them.
| Project | Profile | What they do |
|---|---|---|
| opencue/claude-code-skills | full, skill-writer |
Dogfooding cue on itself |
| recodeee/colony | fleet-control |
Multi-agent coordination MCP |
| recodeee/gitguardex | backend |
Branch + worktree isolation for parallel agents |
Using cue? Open a PR or drop a link in Discussions.
git clone https://github.com/opencue/claude-code-skills.git
cd cue && bun install
bun test # tests (lib + commands)
bun run src/index.ts --help # run locally| Want to | Run |
|---|---|
| Add a skill | cue skills-new <name> then edit resources/skills/skills/<category>/<name>/SKILL.md |
| Add a profile | cue new <name> then cue validate <name> |
| Share your profile | cue share publish --profile <name> |
| Report a bug | Open an issue |
License: MIT.