Agent Toolkit
Manage reusable skills, personas, workflows, and MCP templates across major coding assistants from one toolkit.
- Source repo
- ulises-jeremias/agent-toolkit
- Stars
- ★ 19
- Last updated
- today
- License
- MIT
- Primary language
- V
- FA score
- 71/100 · Some gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformChatGPT · Codex · Claude Code
- Cost
- Free, no paid service needed
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A development team using Claude Code, Cursor, and Copilot can maintain one capability catalog while deploying each client's native configuration.
- Not a fit if
- Teams needing a stable all-in-one distribution: the full-catalog package is experimental and marketplace-pending
- Teams relying on the deprecated profiles/ layout, which must migrate to the plugins/ output
- Teams expecting identical features across targets: Cursor, Copilot, and OpenCode receive different artifacts
- Source review
- 71/100 · Some gaps
What does this agent do, and when should you use it?
Agent Toolkit is a composable capability and runtime layer for AI-assisted software delivery, rather than a standalone model-bound chatbot. Its repository contains skills, agent personas, recurring loops, solution packs, plugins, and MCP templates maintained from shared catalogs and distribution definitions. A native V CLI installs client-specific assets, diagnoses the setup, lists inventory, runs loops, and coordinates multi-agent swarms; a desktop application adds a graphical library, operations view, terminal fleet, and activity insights. Documented targets include Claude Code, Cursor, OpenCode, GitHub Copilot, Windsurf, Pi Agent, and Muse Code, while Agent Plugins 1.0 bundles extend distribution to clients including ChatGPT/Codex. Its outputs stay within the local workspace and target-client configuration boundaries: deployed skill or persona files, native plugin bundles, loop state and reports, and filesystem-backed swarm worktrees and handoffs.
agent-toolkit install detects supported coding assistants and deploys the appropriate skills, personas, and configuration, after which agent-toolkit doctor verifies the setup. agent-toolkit inventory reads the catalogs and capability directories to report the live skill, agent, and loop inventory. Skills are authored as SKILL.md units, personas live under agents/, and product definitions in distributions/products.yaml are compiled into client-facing packages under plugins/. Commands such as agent-toolkit loop run daily-triage execute recurring workflows, write STATE.md and report.md into the loop directory, and apply L1, L2, or L3 mutation-safety policies. agent-toolkit swarm start selects a role recipe and budget, creates a Git worktree for each writer, records state, handoffs, audits, and approvals on the filesystem, and exposes runs through watch and promote. The MCP subsystem supplies registry entries and credential-placeholder JSON templates for GitHub, Slack, Notion, Linear, Figma, ClickUp, and Chrome DevTools.
- A development team using Claude Code, Cursor, and Copilot can maintain one capability catalog while deploying each client's native configuration.
- An open-source maintainer can schedule issue triage, CI sweeps, dependency updates, or PR monitoring with an explicit safety tier for allowed mutations.
- An engineering lead can divide planning, architecture, implementation, review, QA, security, and platform work among narrowly defined personas.
- A team delivering a complex change can use the
pair,team, orfullswarm recipes for isolated worktrees, enforced budgets, audited handoffs, and approval gates. - A developer onboarding a project can start from prepared MCP templates for GitHub, Slack, Notion, Linear, Figma, ClickUp, or Chrome DevTools.
- A user who prefers graphical operations can install the desktop application to browse capabilities, manage jobs and loops, use embedded terminals, and inspect activity reports.
How do you install or deploy this agent?
The recommended product is the native V CLI. With Homebrew:
brew tap ulises-jeremias/homebrew-tap && brew install agent-toolkit
agent-toolkit install
agent-toolkit doctorOn Arch Linux, install the release binary package:
yay -S agent-toolkit-bin
agent-toolkit install
agent-toolkit doctorThe PyPI package is a thin launcher for the bundled V binary:
uv tool install 'agent-toolkit-cli>=1.30.1'
uvx --from 'agent-toolkit-cli>=1.30.1' agent-toolkit install
agent-toolkit doctorThe npm channel is also documented:
npm i -g agent-toolkit-cli
agent-toolkit install
agent-toolkit doctorTo install and launch the desktop application through the CLI:
agent-toolkit gui --install
agent-toolkit guiCore local skills and workflows do not require MCP credentials. If an MCP template is enabled, replace its marked placeholders with credentials for the selected external service.
How do you use this agent?
Install assets for detected clients, verify them, and inspect the available catalog:
agent-toolkit install
agent-toolkit doctor
agent-toolkit inventoryRun the supplied daily triage loop:
agent-toolkit loop run daily-triageInspect swarm recipes and preview a two-role run before allowing execution:
agent-toolkit swarm recipes
agent-toolkit swarm start --recipe pair --dry-run "Add a health check endpoint with tests"Start a team run with the documented Herdr backend, then observe and promote it using the returned run ID:
agent-toolkit swarm start --recipe team --backend herdr "Migrate the auth module"
agent-toolkit swarm watch <run-id>
agent-toolkit swarm promote <run-id>For Agent Skills only, without personas or loops:
npx skills add ulises-jeremias/agent-toolkit -gFor MCP, select a service template from mcp/templates/, replace its credential placeholders, and place the resulting JSON in the target client's MCP configuration location.
What are this agent's strengths and limitations?
- A shared skill and persona catalog targets multiple coding assistants, reducing duplicated prompt configuration across Claude Code, Cursor, Copilot, and other supported tools.
- Loops use explicit L1 proposal-only, L2 controlled-write, and L3 high-autonomy mutation stages, with gates around merge and close operations.
- Swarm orchestration includes role recipes, token/cost/wall-clock budgets, isolated Git worktrees, audited handoffs, bounded feedback rounds, and human approvals.
- Distribution options cover a native CLI, desktop GUI, portable Agent Plugins 1.0 packages, legacy Claude Code plugins, and several system package channels.
- Capabilities, generated products, catalogs, schemas, and validation commands have distinct repository locations, supporting auditable configuration management.
- The broad surface area—skills, personas, loops, plugins, MCP, desktop software, and swarms—creates more setup and governance overhead than a small prompt collection.
- Targets receive different artifacts: Cursor uses plugins or
.mdcrules, Copilot uses an instruction file, and OpenCode uses prompt overlays and agent configurations, so feature parity should not be assumed. profiles/is documented as a deprecated fallback overlay; teams depending on that layout face migration toward the canonicalplugins/output.- MCP templates do not supply service permissions, so adopters must provision and secure credentials for integrations such as GitHub, Slack, Notion, and Linear.
- The full-catalog
agent-toolkit-completepackage is described as experimental and marketplace-pending, which may matter to teams requiring a stable all-in-one distribution.
How does this agent compare with similar options?
Compared with the named classic tmux swarm approach, agent-toolkit swarm is delivered as a single roughly 22 MB V binary and adds built-in pair, team, and full recipes, budget enforcement, a JSON surface, and cross-platform releases. The tmux approach depends on bash, tmux, bb, and a dashboard, although it also provides per-branch packs and first-class handoff auditing. Compared with the repository's legacy Python swarm, the V implementation documents enforced budgets, formal handoff audits, structured observability, and programmatic JSON access without requiring a Python environment.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Agent Toolkit This agent | 71 · Some gaps | CLIFree | ★ 19 | today | V | ChatGPT · Codex · Claude Code |
| Agentic Plugin Marketplace | 70 · Some gaps | Agent plugin / skillFree + model costs | ★ 42k | today | Python | Codex · Claude Code |
| Agor | 68 · Some gaps | CLIFree + model costs | ★ 1.5k | 2d ago | TypeScript | Codex · Claude Code |
| Agency Agents Chinese Expert Library | 48 · Major gaps | CLIFree + model costs | ★ 22k | 5d ago | Shell | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The packet shows explicit permission boundaries: the server binds to localhost by default, remote access requires an explicit flag and token, and destructive routes require confirmation; the Swarm threat model also says worktrees and role policies are not OS sandboxes. Installation offers a dry run, uninstall guidance recommends backups and describes cleanup, and MCP templates require environment-variable placeholders. However, desktop terminals and Swarm runners can access local permissions, and the packet does not show product-level confirmation covering every external effect. Publisher provenance is unverified, so maintainer identity cannot be confirmed.
The repository describes validation workflows, CI, and bounded shutdown behavior, while its security document acknowledges limited test coverage. However, the Swarm security document directly contradicts itself about whether the Claude adapter uses --dangerously-skip-permissions, and the examples depend on several external tools and services; the supplied material does not establish dependency availability. Failure paths and visible startup failures are described, supporting a higher failure-message score.
Target users, supported scenarios, and adaptation paths for several coding assistants are described thoroughly. The packet distinguishes skills, agents, loops, products, packs, and profiles, and documents loop autonomy tiers, MCP/tool boundaries, and Desktop versus CLI use. The sampled skills provide concrete triggers, but coverage is limited, so precision across the full catalog is not established.
The information architecture is extensive; installation and uninstall paths, examples, limitations, permission boundaries, and cleanup risks are documented. The MIT license is clear. Package and plugin versions are present, but the packet does not include release history or a complete maintenance and update commitment; publisher identity is unverified.
The toolkit provides reusable skills, personas, loops, and MCP templates across assistants, with a shared catalog, native CLI, GUI, and dry-run support. This has clear integration value. The sample cannot establish actual output quality, and setup for features such as Swarm and MCP can require substantial configuration.
Core product claims in the README can be cross-referenced against the install guide, plugin manifest, skill samples, desktop code, and security documents. Security materials distinguish stated policy from implementation boundaries and unverified behavior; skills also call for evidence citations and confidence labels. The evidence is still a file sample with no runtime verification, so source traceability and corroboration receive moderate scores.
- The Swarm security document contradicts itself about whether the Claude adapter enables --dangerously-skip-permissions; verify the current implementation and runtime configuration before adoption.
- Swarm runners, the integrated terminal, and MCP can access local permissions or external services. Role policies and worktrees are not a sandbox; review permissions and credential flow before running them.
- Publisher identity is unverified. This is a static sample and cannot establish runtime behavior, dependency state, or coverage of the complete catalog.
Maintain this project? Add the FARS badge to your README
[](https://followagents.com/en/agents/ulises-jeremias-agent-toolkit)<a href="https://followagents.com/en/agents/ulises-jeremias-agent-toolkit"><img src="https://followagents.com/badge/ulises-jeremias-agent-toolkit.svg" alt="FARS review"></a>Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
What's Changed * feat(swarm): record bound People as canonical PersonSessions on real role starts by @ulises-jeremias in https://github.com/ulises-jeremias/agent-toolkit/pull/1609 * fix(swarm): reconcile orphaned PersonSessions on terminal run states by @ulises-jeremias in https://github.com/ulises-jeremias/agent-toolkit/pull/1611 * fix(desktop): send explicit JSON object body for bodyless mutations by @ulises-jeremias in https://github.com/ulises-jeremias/agent-toolkit/pull/1612 …View on GitHub ↗ -
Release notes excerpt
What's Changed * docs(web): refresh site screenshots + demo from Desktop 1.47.4 by @ulises-jeremias in https://github.com/ulises-jeremias/agent-toolkit/pull/1586 * chore(deps): bump the codeql-action group with 2 updates by @dependabot[bot] in https://github.com/ulises-jeremias/agent-toolkit/pull/1578 * chore(release): prepare v1.47.5 by @ulises-jeremias in https://github.com/ulises-jeremias/agent-toolkit/pull/1587 * fix(people): import canonical Munder hire fields without silent loss by @ulises-jeremias in https://github.com/ulises-jeremias/agent-toolkit/pull/1589 …View on GitHub ↗ -
Release notes excerpt
What's Changed * fix(world): neon place glow for Cyberpunk City by @ulises-jeremias in https://github.com/ulises-jeremias/agent-toolkit/pull/1584 * chore(release): prepare v1.47.4 by @ulises-jeremias in https://github.com/ulises-jeremias/agent-toolkit/pull/1585 Full Changelog: https://github.com/ulises-jeremias/agent-toolkit/compare/v1.47.3...v1.47.4View on GitHub ↗
FAQ
Does adoption require a particular model provider?
Can a loop modify or merge repository content automatically?
Do MCP integrations require additional permissions?
Can I install only the skills?
npx skills add ulises-jeremias/agent-toolkit -g installs the Agent Skills-compatible content, but it does not include personas or loops.How are broken installations or definitions detected?
agent-toolkit doctor. Contributors can also run ./scripts/validate-skills.vsh and ./scripts/validate-loops.vsh; the validators exit nonzero and print human-readable errors when checks fail.Thanks — we use this to improve the page.