openclaw
Skills for the OpenClaw personal AI assistant, covering browser automation, routing requests to coding agents, presenting canvas widgets, running apps on temporary machines, and sharing diffs.
78 skills394k
@steipeteAgent Orchestration
Plugin
superlite
A fast software factory workflow for Claude Code: one approval gate, parallel waves, routed models.
Claude Code
> /plugin marketplace add iha2/superlite> /plugin install superlite@superlite-dev
Codex
$ npx skills add iha2/superlite --skill diagnosis drafting feature-prototype inventing mvp-prototype proof research shipping swarm testing using-superlite writing-specs -a codex
Cursor
$ npx skills add iha2/superlite --skill diagnosis drafting feature-prototype inventing mvp-prototype proof research shipping swarm testing using-superlite writing-specs -a cursor
Gemini CLI
$ npx skills add iha2/superlite --skill diagnosis drafting feature-prototype inventing mvp-prototype proof research shipping swarm testing using-superlite writing-specs -a gemini-cli
GitHub Copilot
$ copilot plugin marketplace add iha2/superlite$ copilot plugin install superlite@superlite-dev
OpenCode
$ npx skills add iha2/superlite --skill diagnosis drafting feature-prototype inventing mvp-prototype proof research shipping swarm testing using-superlite writing-specs -a opencode
Windsurf
$ npx skills add iha2/superlite --skill diagnosis drafting feature-prototype inventing mvp-prototype proof research shipping swarm testing using-superlite writing-specs -a windsurf
What's inside
12 Skills
/diagnosisUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes/draftingUse when you have an approved design or requirements for a multi-step task and need an implementation plan, before touching code./feature-prototypeUse in feature mode after the feature plan is approved, to cut the smallest runnable container of an existing app for the prototype build
19 Commands
8 Agents
final-reviewerFresh one-turn final reviewer. Reviews from .superlite/review-packet.md alone (Read only) and returns a verdict plus tiered findings. Findings only; never fixes.fixer-opusFix-only agent, tier 3. Diagnoses unknown-cause findings (reproduce, then fix) with a regression test, then records a checkpoint.fixer-sonnet-highFix-only agent, tier 2. Fixes known-cause findings that span modules or a seam, or known probe classes, with regression tests, then records a checkpoint.
README
A software factory. Approve a plan once, then it builds the code.
Use it
Install it (below), open a session in your project, and say what you want. superlite shows a one-screen intro the first time; /superlite:intro brings it back and /superlite:help has every detail.
Each run starts its own session automatically (superlite-cli session ensure): a branch superlite/sessions/<topic> in your checkout, or a parallel worktree if another run is still open. Shipping closes it. See Sessions.
Say what you want
| Situation | Say something like | What happens |
|---|---|---|
| MVP, a new project | "Build me a static site generator from this spec" | One batch of questions, a plan, then parallel tasks on Sonnet and Haiku, package reviews and one fresh final review |
| A feature on existing code | "Add CSV export with column widths to the existing app" | Feature mode: it researches the code (Graphify on a large codebase, never installed without your yes), writes a feature plan you validate, builds a small prototype in its own worktree for you to try, then ports it into your code with frozen interfaces and seam checks. The report shows both builds |
| Debug | "This test fails on leap days: find the root cause and fix it" | diagnosis finds the cause first; fixes go to fix-only agents by tier, each leaving a note, and escalate after two failed rounds |
| Research | "Research the state of the art in vector search, for a VP" | Research mode: parallel researchers fill a sourced ledger, contradictions are listed with causes, and the report is written at your level (Director, VP, Researcher or Simple) with the same claims and citations at every level |
| A small change | "Rename build to render everywhere" | Small work stays inline, with a reviewer always |
| Review and harden | "Review this branch and fix what you find" | Package reviewers fix their own findings; the final reviewer reports findings with tiers and never edits |
| You approve first | "Build X. I will approve the plan" | A human orchestrator: you get a plain-language review plan with diagrams; nothing runs until you say yes |
| Hands off | "Build X. I am away, decide yourself" | The AI orchestrator plans, lints, dispatches and rules on open choices without stopping |
| Ship it | "We are done: finish the branch" | Verification first, then merge or PR options. It never pushes without you |
Or use a command
| Command | What it does |
|---|---|
/superlite:start [mode] [what] | A menu: superlite suggests the mode for your request (regular, MVP, feature, debug, small, review, research), you confirm it and pick who orchestrates |
/superlite:mvp <what> | Plan the smallest working version on a clickable HTML prototype, then build it |
/superlite:feature <change> | Change existing code: a plan you validate, a prototype you try, then the integration with seam checks |
/superlite:debug <bug> | Root cause first, then a fix with a regression test |
/superlite:research <topic> | Research a topic with parallel agents: a sourced ledger, then a report at your level |
/superlite:small <change> | A small change inline, without the planning flow |
/superlite:human, /superlite:ai, /superlite:approve | Choose who orchestrates; approve the review plan |
/superlite:status, /superlite:stop, /superlite:resume | Watch, stop or resume a build |
/superlite:agents, /superlite:tail | Watch a run: the agent map pane, or the same run as a terminal feed without the mod |
/superlite:review, /superlite:report, /superlite:finish | Review a branch, read build reports, finish the branch |
/superlite:setup, /superlite:intro, /superlite:help [section] | First-run check, the intro screen, the detailed help |
Plain words work just as well; the commands are shortcuts.
Who orchestrates
- Human orchestrator. You get a plain-language review plan with diagrams (a
.review.md, about two pages, with a rough time and cost), and nothing is linted, dispatched or sent to an agent until you reply approve. Any clear approval counts (yes, go ahead, looks good, or similar), including a longer note. After that you are not asked again: any change to scope is recorded as a ruling and listed at the end under "Changed from the approved plan". Small inline work needs only your yes in chat. - AI orchestrator. It plans, lints, dispatches and rules on open choices itself, with no review plan and no questions.
Both stop for destructive, outward (push, merge, publish) or security-sensitive actions, and superlite never commits during a run: finished tasks are hidden checkpoints. A checkpoint is a hidden save of one task under refs/superlite/*. At session end, shipping asks once: "Commit to " or "Leave uncommitted".
Watch a run
Let it run. Watch .superlite/ in your project: progress.md has the rulings and the log, test-summary.json the latest test result, metrics.jsonl and the run history the time and cost per agent.
flowchart LR
A([Your request]) --> B[Plan]
B --> C[Build in parallel]
C --> D[Review and fix]
D --> E([Done])
A read-only view, offered when you approve the plan (reply approve map), or opened any time:
/superlite:agentsopens the agent map in Claude Desktop: a tree from the main session down, each agent under the one that spawned it, green while it runs, red if it was aborted or blocked, grey when done. Each node shows its tier, time, tokens and tasks (✓ once checkpointed); click a row for its details and its ledger lines. It needs theclaude-agent-mapmod:/plugin install claude-agent-map@superlite-dev.- Without the mod (a terminal session, another harness),
/superlite:tailprints the same run as a live feed: every agent start and finish frommetrics.jsonland every ledger line fromprogress.md(superlite-cli tail --dir .superlite).
Install
You need Claude Code, git, Python 3.10 or newer (the tools are Python; the project you build can be in any language), and bash (Git Bash on Windows). uv is optional.
/plugin marketplace add iha2/superlite
/plugin install superlite@superlite-dev
Optional, for the agent map pane in Claude Desktop: /plugin install claude-agent-map@superlite-dev. Superlite works without it; in a terminal use /superlite:tail.
Or load a local checkout for one session: claude --plugin-dir <path-to-superlite>
Open a fresh session: the superlite intro appears once. Then send Let's make a react todo list; a working install starts inventing before any code is written. Installs for Codex, Cursor, Gemini CLI, OpenCode and the other harnesses are in Installation below.
What it is
superlite plans a build, splits it into tasks that can run side by side, hands each task to the cheapest agent that can do it well, checks the seams, and reviews the result. You decide who orchestrates: you, or the AI.
- Autonomous. Describe the project, pick the AI orchestrator, and walk away. Decisions it has to make are recorded as rulings, not asked as questions.
- Fast. Up to 18 agents at once (measured in run k1; the dispatch cap is now 10 running tasks), a plan written for parallelism, and mechanical work on Haiku.
Not a rival to superpowers
superlite is not a competitor to superpowers. superpowers is a careful, collaborative workflow that keeps a human close to every step, and it is excellent at that. superlite starts from its ideas (the plugin layout, the session-start hook, the lifecycle skills, with credit) and tunes them for a different job: autonomous development, at speed. If you want to steer each step, use superpowers. If you want to hand over a spec and come back to working code, use superlite. A superlite run suspends superpowers until superlite-cli finish; after that, superpowers can be used again.
It is fast
Same machine, same task: build a Python site generator and a spreadsheet engine from one spec (sitegen + minisheet, 177 hidden tests), headless on Opus.
| What we measured | superpowers | superlite |
|---|---|---|
| Wall-clock to a finished build | 33.6 min (stock, 3 runs: 21.2 / 31.9 / 47.6)23.5 min (orchestrated, 3 runs) | 16.1 min |
| Faster than superpowers | 52% vs stock, 31% vs orchestrated | |
| Fastest-to-slowest spread, 3 runs | 26.4 min | 9.1 min |
| Agents working at once | 3 to 4 | up to 18 (k1; dispatch now caps at 10 running tasks) |
| Hidden tests passed | 177 / 177 | 177 / 177 (a tie, at higher speed) |
| Earlier 9-module benchmark (1 run each) | 34.4 min | 8.8 min |
| superlite against its own first version | 26.9 min | 16.1 min (40% faster) |
And it is not tied to one language. A TypeScript site generator went from spec to 132 / 132 hidden tests in 8.5 minutes.
The 16.1 min figure is one run of the current build. The superpowers figures, the spread row (3 runs of each, on an earlier superlite build) and the 9-module row (the first version, 1 run each) come from earlier runs on the same machine, so treat the gaps as indications, not a statistical proof. superlite can cost more than superpowers and scores lower on the extra robustness probes (4 of 7 against about 5.7 of 7). Details, runs and caveats: bench/ and the Benchmark section below.
More
How it works, in docs/: how a run works · skills and agents · hooks · tools · config · language support · how the rules are enforced · an example review plan. Installation for other harnesses, the benchmark harness and the task list follow below.
Configuration
detail(plan switch).draftingrecords**Detail:** contracts | tests | fullin the plan header, and a task can override it.contractsgives files, signatures and named tests with exact values.tests(the default) adds the test code verbatim and leaves the implementation to the implementer.fullincludes implementation code too, for tricky algorithms.inventingasks for it in its single batched question, and picks the default itself when unattended.- Final review. The coordinator runs at medium effort. The final review is a fresh Opus
final-reviewerat high effort: one turn, findings only, reading a review packet built from the logs, with a target under 30 s. It is not a fork, soCLAUDE_CODE_FORK_SUBAGENTis not needed.
Stars on GitHub
Momentum
- stars in total
- 311
File tree
Similar plugins.
@steipeteorca
Gives Claude Code users skills to drive Orca-managed worktrees, terminals and the embedded browser through the orca CLI, plus Jira and Linear ticket work and inline HTML chat visuals. Covers chart, table and mockup output.
12 skills1 MCP124k
@stablyaipaperclip
Orchestrates teams of AI agents to run work like a company, with a Node.js server and React UI. Adds skills for delegating tasks, following up on results, reviewing team status, and managing Paperclip tasks from Hermes.
22 skills4 agents1 MCP+2+1+1113k
@paperclipailobehub
Organizes your AI agents for round-the-clock operation, with tools to hire, schedule and report on your agent team. Lets you oversee the agents without staying online yourself.
85k
@lobehubQuestions about superlite.
A fast software factory workflow for Claude Code: one approval gate, parallel waves, routed models. Install it with the command on its page. It includes diagnosis, drafting, feature-prototype. Its skills do not fire on their own yet. Free and open source.
- What is superlite?
- A fast software factory workflow for Claude Code: one approval gate, parallel waves, routed models.
- How do I install superlite?
- Run these in Claude Code: /plugin marketplace add iha2/superlite then /plugin install superlite@superlite-dev. Then prompt normally.
- Does superlite auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin.
- Is superlite free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.
- Which coding agents can use superlite's skills?
- superlite installs in Claude Code, and its skills also install in Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI. Each skill's page has the install command. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it