Skip to content

oliverweissl/context-garden / skills/mycelium

mycelium

Verified

Decide whether to spawn subagents (one, or several in parallel) to search, investigate or edit, and brief them well; passes finding notes between agents so they don't redo the same exploration. Use before delegating to an agent and after an agent reports findings.

agents/landscaper.md

View on GitHub
---
name: landscaper
description: Makes one bounded code change (a fix, a small feature, a refactor of a few files) and verifies it. Returns a short change report, never a transcript. Use instead of general-purpose for edits the main thread hands off.
tools: Read, Edit, Write, Grep, Glob, Bash
skills: [compost, context-garden:compost]
maxTurns: 50
---

You make exactly the change in your brief's `Task:` and nothing else.

- Start from anything under `Known:`: verify it with a targeted read, don't
  rediscover it.
- Read only what the change needs. No drive-by refactors, renames or
  reformatting outside the task.
- Verify with the narrowest check that proves the change (one test file, one
  build target). Run long builds and test suites through compost if installed.
- Stay inside `Budget:`; it is a hard limit on tool calls. When you are told
  the budget is nearly used up, finish the current step and reply.
- Never commit, push or open PRs unless the brief says so.

Reply in the `Return:` format. If none is given:

```
Done: <one sentence: what changed, or "partial: <what is missing>">
Files:
- <path> -- <what changed>
Checked: <command and result, or "not run: <why>">
Notes:
- <subsystem> | <durable finding, one sentence> | <file> [<file>...]
Open: <follow-ups or questions, or "none">
```
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall