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 commands/skywalker2506/ccplugin-opencode-bridge/opencodegit clone --depth 1 https://github.com/SkyWalker2506/ccplugin-opencode-bridgeWhat 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 | $0.00000 | $0.01420 |
| Opus 5 | $0.00000 | $0.00710 |
| Sonnet 5 | $0.00000 | $0.00284 |
| Haiku 4.5 | $0.00000 | $0.00142 |
Grade A, and why
opencode 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 yesterday.
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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/opencode
Manage OpenCode/Zen connections, switch models, and configure local Ollama.
Usage
| Command | Behavior |
|---|---|
/opencode |
Show current OpenCode setup status (Zen + Ollama) |
/opencode zen |
Connect to Zen cloud, set free model (gpt-5-nano) |
/opencode local |
Switch to Ollama local model (qwen2.5-coder:7b) |
/opencode models |
List available models (Zen free + Ollama pulled) |
/opencode pull <model> |
Pull an Ollama model (e.g., gemma3:4b, qwen2.5-coder:7b) |
/opencode config |
Show and edit ~/.config/opencode/opencode.json |
/opencode install |
Install or update OpenCode CLI (npm install -g opencode-ai) |
Execution
Default: Show Status
When invoked without arguments, run the status script:
bash ~/.claude/plugins/opencode-bridge/scripts/opencode-status.sh
Display the output. The script checks:
1. Check if OpenCode CLI is installed:
- Run: which opencode
- If missing, offer to install: npm install -g opencode-ai
2. Check Ollama status:
- Run: ollama list 2>/dev/null
- Show pulled models or note that Ollama is not running
3. Check config file:
- Read: ~/.config/opencode/opencode.json
- Show current model, small_model, enabled_providers
4. Display summary:
OpenCode Bridge Status
----------------------
CLI: installed (vX.X.X) | not installed
Zen: connected (model: opencode/gpt-5-nano) | not connected
Ollama: running (models: qwen2.5-coder:7b, gemma3:4b) | not running
Config: ~/.config/opencode/opencode.json
Providers: ["opencode", "ollama"]
/opencode zen -- Connect to Zen Cloud
1. Verify OpenCode CLI is installed (install if missing)
2. Check if ~/.config/opencode/opencode.json exists
- If not, copy from ~/Projects/claude-config/templates/opencode.json
3. Remind user to authenticate:
- "Run `opencode` then `/connect` -> select `opencode` -> paste API key from https://opencode.ai/auth"
- Or set env: export OPENCODE_ZEN_API_KEY='sk-...' in ~/.zshrc
4. Set model to opencode/gpt-5-nano (default free tier)
5. Show available Zen free models:
Zen Free Models
---------------
opencode/gpt-5-nano -- Free tier (default)
opencode/minimax-m2.1-free -- Free, limited time
opencode/glm-4.7-free -- Free, limited time
opencode/kimi-k2.5-free -- Free, limited time
opencode/big-pickle -- Free, limited time
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.
- yesterday First seen · 153 lines · 0 tokens per session scan A 17272334e1ae
opencode is a command published in the GitHub repository SkyWalker2506/ccplugin-opencode-bridge (3 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,420 tokens. 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 2026-08-31.
Other commands, from other repositories
feature-develop-hermit
Same outline as /feature-develop, but the Phase 3 implementation is delegated to Hermit over MCP so Claude's context never absorbs the grunt-work tool output.
code-polish-hermit
Unlike /code-polish, this variant is a distributed state machine. Hermit runs its own review-and-apply loop until it is self-clean, and Claude provides two independent review passes on top as a quality gate. Claude's token spend is capped at 2 review rounds.
code-apply-hermit
Hands the P1–P5 findings from the most recent /code-review to Hermit so Claude doesn't burn tokens re-reading every file and retyping every edit. Claude stays on judgment; Hermit does the mechanical apply.
code-push-hermit
Commit-and-push are the textbook grunt-work target: short, mechanical, deterministic, and unrelated to reasoning. This skill keeps the deciding parts in Claude and delegates the git commands to Hermit.
toefl-grade
TOEFL 답안/녹음 채점 — 로컬 LLM(Ollama)과 whisper.cpp로 4개 영역을 채점하여 SCORES.md에 점수를 누적 기록한다.
toefl-practice
TOEFL 유형 문제 생성 — 로컬 LLM(Ollama)이 reading/listening/speaking/writing 영역의 실전형 문제를 생성하여 practice/에 저장한다.