# Superlazy Subagents

> Silent subagent-driven plan execution. Use when executing an implementation plan with independent tasks and subagent support is available.

- **Type:** Skill
- **Install:** `agentstack add skill-starchybomb-superlazy-superlazy-subagents`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [StarchyBomb](https://agentstack.voostack.com/s/starchybomb)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [StarchyBomb](https://github.com/StarchyBomb)
- **Source:** https://github.com/StarchyBomb/superlazy/tree/main/skills/superlazy-subagents

## Install

```sh
agentstack add skill-starchybomb-superlazy-superlazy-subagents
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Superlazy Subagents

SUPERLAZY mode: output ≤3 lines (questions / user-actions / ✅❌); minimal code, full quality; do the work, never narrate it.

## Loop (per task, no user check-ins between tasks)
1. Extract the task's text to a brief FILE. Dispatch a fresh implementer subagent: one line of project context + brief path + interfaces/decisions from earlier tasks + report-file path. NEVER paste session history or prior-task summaries; never make it read the whole plan.
2. Implementer questions → answer, re-dispatch. BLOCKED → more context, stronger model, or split the task — never blind retry.
3. Review the task: generate diff as a FILE (`git diff BASE..HEAD`, BASE recorded before dispatch — not `HEAD~1`), dispatch a reviewer with brief + report + diff paths + verbatim spec constraints. Never pre-judge findings ("don't flag X") in the prompt.
4. Critical/Important findings → one fix subagent with ALL findings, then re-review. Minor → ledger.
5. Append to ledger file (`.superlazy/progress.md`): `Task N: complete (commits X..Y)`. Ledger survives compaction — trust it + `git log` over memory; NEVER re-dispatch a task it marks complete.
6. All tasks done → one final whole-branch review (merge-base diff file, most capable model). Findings → ONE fixer for the full list. Then `✅`.

## Cost rules
- Cheapest model that fits, stated explicitly per dispatch: transcription-from-plan/1-file fixes → cheapest; multi-file integration or prose-spec implementers and reviewers → mid-tier; architecture + final review → most capable. Turn count beats token price — too-cheap models take 2-3× turns.
- Artifacts move as files (brief, report, diff), never pasted text.
- Never dispatch implementers in parallel (conflicts). Never skip re-review after fixes.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [StarchyBomb](https://github.com/StarchyBomb)
- **Source:** [StarchyBomb/superlazy](https://github.com/StarchyBomb/superlazy)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-starchybomb-superlazy-superlazy-subagents
- Seller: https://agentstack.voostack.com/s/starchybomb
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.