Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/fmflurry/settings-opencode/treetopianpx skills add fmflurry/settings-opencode --skill treetopiagit clone --depth 1 https://github.com/fmflurry/settings-opencodeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00051 | $0.00927 |
| Opus 5 | $0.00026 | $0.00464 |
| Sonnet 5 | $0.00010 | $0.00185 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
treetopia scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Treetopia
Create an isolated OpenCode worktree whenever the user explicitly wants branch isolation, parallel feature work, or protection from branch collisions.
Trigger Rules
Use this skill only when the user explicitly says one of these intents:
- Create a worktree.
- Use a worktree.
- Use an isolated worktree.
- Create a parallel feature branch.
- Avoid branch collision.
- Keep two agents or two features from sharing one branch.
Do not use this skill merely because the user asks for normal implementation, refactor, testing, or feature work. Ordinary feature work stays in the current checkout unless the user explicitly requests isolation.
Purpose
Prevent two primary agents or two active features from sharing the same branch and overwriting or colliding with each other's changes.
Start Workflow
When triggered:
- Derive a concise branch name from the user's task.
- Use lowercase words separated by hyphens.
- Prefer a short prefix such as
feature/,fix/, orchore/when obvious. - Keep the name specific enough to identify the task.
- Determine the base branch.
- If the user names a base branch, use that branch.
- Otherwise, default to the current branch.
- Immediately call
worktree_create.- Pass the derived branch name.
- Pass the base branch only when the user named one or the tool requires it.
- Continue development inside the new worktree/session created by the tool.
Example tool intent:
worktree_create(branch: "feature/customer-import", baseBranch: "main")
If no base branch was named:
worktree_create(branch: "fix/login-timeout")
Development Guidance Inside Worktree
- Treat the worktree as the isolated task workspace.
- Follow normal project instructions, architecture rules, and verification gates.
- Do not assume the original checkout has your worktree changes.
- Avoid cross-worktree edits unless the user explicitly asks.
- Preserve the verification gate before proposing teardown, merge, or cleanup.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 111 lines · 51 tokens per session scan A 957de7ba9e0c
treetopia is a skill published in the GitHub repository fmflurry/settings-opencode (172 stars, last pushed 20d ago), licensed MIT. It adds 51 tokens to every session and 927 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…