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/zai-org/synapse/opencode-controllernpx skills add zai-org/Synapse --skill opencode-controllergit clone --depth 1 https://github.com/zai-org/SynapseWhat 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 | $0.00036 | $0.00415 |
| Opus 5 | $0.00018 | $0.00208 |
| Sonnet 5 | $0.00007 | $0.00083 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
opencode-controller 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.
What it actually says
Opencode Controller
Core rule
Clawdbot does not write code. All planning and coding happens inside Opencode.
Pre-flight
- Ask the user which AI provider to use.
- Ask how the provider should be authenticated.
- Do not proceed without confirmation.
Session management
- Start Opencode.
- Open session selector using: /sessions
- If the current project already exists:
- Select the existing session.
- Never create a new session without user approval.
Agent (mode) control
- Open agent selector using: /agents
- Available agents:
- Plan
- Build
- Always select Plan first.
- Switch agents whenever required using
/agents.
Model selection
- Open model selector using: /models
- Select the user-requested provider.
- If authentication is required:
- Copy the login link provided by Opencode.
- Send it to the user.
- Wait for confirmation before continuing.
Plan agent behavior
- Ask Opencode to analyze the task.
- Request a clear step-by-step plan.
- Allow Opencode to ask clarification questions.
- Review the plan carefully.
- If the plan is incorrect or incomplete:
- Ask Opencode to revise it.
- Do not allow code generation in Plan.
Build agent behavior
- Switch to Build using
/agents. - Ask Opencode to implement the approved plan.
- If Opencode asks any question:
- Immediately switch back to Plan.
- Answer and confirm the plan.
- Switch back to Build.
Completion
- Repeat the Plan → Build loop until all user requirements are satisfied.
- Never skip Plan.
- Never answer questions in Build.
Output format
- Show all slash commands explicitly.
- State which option is selected.
- Provide login links verbatim.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- _meta.json 138 B
- .clawhub/origin.json 151 B
- assets/operator-prompts.md 382 B
- references/command-cheatsheet.md 157 B
- references/failure-handling.md 305 B
- references/model-selection.md 320 B
- references/plan-vs-build.md 251 B
- references/question-handling.md 195 B
- references/session-management.md 328 B
- references/workflow.md 336 B
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 · 78 lines · 36 tokens per session scan A 6535df08ba8b
opencode-controller is a skill published in the GitHub repository zai-org/Synapse (434 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 415 once invoked, about $0.0002 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…