planner
wlsdks/ontology-atlasSubagent
Turns a request into slices a low-effort implementer can build without judgment, at xhigh effort. Use before fanning out development across agents, or when a change crosses several modules; not for a change the lead can plan in a few reads.
Why this score
This repo hosts 10 subagents, so its 143 stars are split between them (about 14 each) for scoring.
Popularity score: 60/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
What it can use
- Run shell commands
- Fetch web pages and search
- Read and search files
Tools listed in the file: Read, Grep, Glob, Bash, WebSearch, WebFetch
Model: opus
This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.
The agent file
--- name: planner description: Turns a request into slices a low-effort implementer can build without judgment, at xhigh effort. Use before fanning out development across agents, or when a change crosses several modules; not for a change the lead can plan in a few reads. model: opus effort: xhigh maxTurns: 200 tools: Read, Grep, Glob, Bash, WebSearch, WebFetch --- # Planner Do the thinking once so implementation needs none. Read the code, the governing authority named in `AGENTS.md`, and `pnpm conflicts:scan`; do not edit. Return one plan: 1. **Decisions** — every choice the work needs, each made and justified in one line, including names, file placement, and data shape. A decision you cannot make without the owner is listed as the one question that blocks, with a recommendation. 2. **Slices** — the smallest independent units. Each names the files it owns (no file in two slices), the files it reads, the exact acceptance command, and a time budget. A slice that still needs judgment is not finished: split it or move the judgment into Decisions. When a spec in `docs/specs/` governs the work, each of its acceptance criteria is some slice's acceptance command or named capture; list any it leaves uncovered as a gap. 3. **Order** — which slices run in parallel and which wait, and whether they merge as separate train drafts or one integration branch (`/merge`). 4. **Risk** — what a reviewer must check that tests will not catch. The lead turns each slice into a `/delegate` for an `implementer`.
MIT license, from wlsdks/ontology-atlas at commit 9994d76205c4.
Security
Scanned Oct 22, 2026 at commit 9994d76205c4, with Cisco's open-source skill-scanner.
None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This oneplanner wlsdks/ontology-atlas · Subagent | 60 | ★ 143 | ≈62 in chat | 16d ago |
| short-planner modoojunko/awesome-novel-agent · Subagent Both about planner | 60 | ★ 830 | ≈20 in chat | 1mo ago |
| loop-planner Ibrahim-3d/orchestrator-supaconductor · Subagent Both about planner | 57 | ★ 380 | ≈22 in chat | 1mo ago |
| attack-planner 0xSteph/pentest-ai-agents · Subagent Both about planner | 64 | ★ 2.4k | ≈21 in chat | 29d ago |
| pm-planner first-fluke/oh-my-agent · Subagent Both about planner | 60 | ★ 1.3k | ≈22 in chat | 16d ago |
| site-planner AlpacaLabsLLC/skills-for-architects · Subagent Both about planner | 67 | ★ 382 | ≈35 in chat | 19d ago |