Free · Open source · MIT

Vibe Coding is Dead.
Start Agent Engineering.

One command. /agt classifies your task, dispatches a team of agents, and routes the right Claude model to each — in your voice.

One commandOpus plans · Sonnet buildsReview built inOpen source
Live demoOne command

Watch it orchestrate.

Type one command. agentille classifies, plans, dispatches agents, and ships.

claude-code — agentille

$ /agt "refactor the dashboard sidebar to be collapsible"

→ classifying… feature

→ planning · Opus … 3 steps, 2 parallel

→ dispatching · executor ×2 · Sonnet

→ code review · Opus … ✓ no blockers

→ design review · Opus … ✓ 3 viewports · axe clean

✓ done · PR #42 · feature-team (4 teammates · 12m)

Five specialists. Always the right one.

agentille routes tasks to the agent built for them — not a generic chatbot doing everything at once.

Opus

planner

Goal-backward plan with parallel-step markers

Sonnet

executor

Headless implementation, atomic commits, adaptive PR/push

Opus

code-reviewer

Bugs, security, quality — read-only, severity-classified

Opus

design-reviewer

6-pillar visual review, axe-core, AI-design-tell scan

Opus

security-reviewer

Secret leaks, injection, auth bypass — severity-classified

Model routing

Tokens go where they earn the most.

Each model does exactly the job it's priced and capable for. No Opus on boilerplate. No Haiku on architecture.

Opus

Thinks hard so executors don't have to

  • Goal-backward planning
  • Architecture decisions
  • Code review
  • Design review
  • Security review

Sonnet

Fast, capable, ships the actual code

  • All execution & coding
  • File edits & commits
  • Adaptive integration (PR / push / local)

Haiku

Dirt-cheap, runs at the edges

  • Task classification
  • Final summary
  • Short-circuit no-ops
Optional~4× tokens

Team mode — one agent per pane

Opt in with /agt --team feature-team "...". Each teammate gets its own tmux/iTerm2 pane. Costs more — worth it for complex features or high-stakes reviews.

feature-team

2× executor + code-reviewer + design-reviewer. Ship a feature end-to-end.

review-team

code + design + security reviewer. Full audit on a PR before merge.

incident-team

3× executor, competing hypotheses. Race to a fix under pressure.

The old way vs. the one command

Spoiler: agentille does the chaining for you now.

before

Do it by hand

  1. 01figure out the plan yourself
  2. 02pick the right model for each step
  3. 03remember to actually switch models
  4. 04branch + isolate the work
  5. 05build it
  6. 06remember to review it
  7. 07catch the UI regressions yourself
  8. 08open the PR by hand
  9. 09pray nothing conflicts
after

agentille

/agt "build the feature"

✓ done

(the orchestrator handled the rest)

Claude Code pluginMIT · Free

Install the plugin.

Inside Claude Code. Takes two minutes. Then /agt is ready everywhere.

claude-code — setup

Requires Claude Code (recent version; 2.1.32+ for team mode).

No CLI? Build your profile in the browser →

What you get

Orchestration benefits — not config files.

01

One-command orchestration

Type /agt "task" and the system classifies, plans, dispatches agents, reviews, and summarizes — you don't wire anything.

02

Right model per job

Opus for planning and review, Sonnet for execution, Haiku for cheap classification. Tokens go where they earn the most.

03

Parallel-safe worktrees

Each executor branches off your current branch in its own git worktree. Atomic commits, then integrates adaptively — PR, push, or local branch.

04

Voice-aware from day one

Your profile.json shapes every prompt. Set brutal honesty once — every planner, executor, and reviewer speaks the same way.

05

Review built in

Code review on every change. Design review whenever UI is touched. Security reviewer available on demand. No extra step.

Audit it, fork it, ship it.

No black box. The entire orchestration is readable code. See exactly how agents are dispatched, models are routed, and your voice is applied.

By @hasuwini77

Star on GitHub

github.com/hasuwini77/agentille

Ready to orchestrate?

One command. Every agent. The right model at every step.

Install the plugin →

or build your profile in the browser →