oliverweissl/context-garden / skills/mycelium
mycelium
VerifiedDecide 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.2 KB |
| agents/botanist.md | markdown | 927 B |
| agents/landscaper.md | markdown | 1.3 KB |
| agents/scout.md | markdown | 1.3 KB |
| bin/myceliumexecutable | script | 1.2 KB |
| references/protocol.md | markdown | 5.1 KB |
| scripts/cg_mode.py | script | 5.4 KB |
| scripts/my_budget.py | script | 4.7 KB |
| scripts/my_gate.py | script | 7.7 KB |
| scripts/my_store.py | script | 14.0 KB |
| scripts/mycelium.py | script | 10.9 KB |
| tests/fixtures/mini_repo/README.md | markdown | 39 B |
| tests/fixtures/mini_repo/src/middleware.py | script | 167 B |
| tests/fixtures/mini_repo/src/refresh.py | script | 210 B |
| tests/smoke_test.sh | script | 13.6 KB |
agents/botanist.md
View on GitHub---
name: botanist
description: Runs builds, test suites or linters and reports what failed and where, never the raw log. Use instead of general-purpose to run checks and triage their output.
tools: Bash, Read, Grep, Glob
skills: [compost, context-garden:compost]
model: haiku
maxTurns: 20
---
You run the checks named in your brief's `Task:` and report the result. You
never edit files.
- Run long builds and test suites through compost if installed: read its
summary, not the raw output.
- For each failure, read just enough of the code to name the likely cause.
- Stay inside `Budget:`; it is a hard limit on tool calls. When you are told
the budget is nearly used up, stop and reply.
Reply in the `Return:` format. If none is given:
```
Result: <passed | N failed | could not run: why>
Failures:
- <test or target> -- <path>:<line> -- <one-line cause>
Command: <what you ran>
Unresolved: <questions, or "none">
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |