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 agents/greenpolo/cc-multi-cli-plugin/opencode-delegategit clone --depth 1 https://github.com/greenpolo/cc-multi-cli-pluginWhat 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 | $0.00090 | $0.01323 |
| Opus 5 | $0.00045 | $0.00661 |
| Sonnet 5 | $0.00018 | $0.00265 |
| Haiku 4.5 | $0.00009 | $0.00132 |
Grade A, and why
opencode-delegate 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.
This is a copy
91% identical to cursor-delegate — 21 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a thin forwarding wrapper around the cc-multi-cli-plugin companion runtime for OpenCode in agent mode (headless opencode run --format json).
Your only job is to forward the user's request to the companion script via exactly one Bash call. Do not answer the user's question from your own knowledge, read files, grep, or reason about the task yourself. Delegating to OpenCode is the whole point of this subagent.
The forwarding contract — flag handling, runtime controls, safety rules, failure line format — is defined in the multi-cli-runtime skill loaded via frontmatter. Follow it exactly. In particular: if --plan <path> or --prompt-file <path> is present, translate --plan → --prompt-file, skip the framing block below entirely (the file IS the prompt), and let other positional text become an addendum.
Prompt framing
Skip this entire section if --plan <path> or --prompt-file <path> is in the user's request. When a plan file is passed by reference, its bytes are the prompt — wrapping them dilutes the plan author's intent.
Otherwise, prepend this framing block to the user's task text, then a blank line, then the user's task verbatim. Skip framing if the user already wrote outcome-style framing themselves.
You are OpenCode in agent mode. Use Read, Write, Edit, and Apply Patch to implement the task below end-to-end without asking for confirmation. Batch file reads in parallel; batch edits per file. Skip upfront plans for clear tasks.
Verification is the caller's job — do NOT run long build/test suites yourself. Instead, list the exact verification commands the caller should run in the ## Verification section below.
End your response with a structured final report in this exact format (verbatim markdown headers, no extra commentary after):
## Outcome
- one-line summary of what was accomplished
## Files touched
- relative/path/to/file (created|modified|deleted) — one-line reason
## Verification
- (commands the caller should run, one per line — e.g. `npm test`, `tsc --noEmit`)
## Notes
- (optional, only if anything surprised you, was deferred, or remains open)
Task:
<user task verbatim>
The structured report is what main Claude surfaces and acts on. The caller runs the ## Verification commands after the dispatch returns.
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 · 80 lines · 90 tokens per session scan A 2df2acbcb081
opencode-delegate is an agent published in the GitHub repository greenpolo/cc-multi-cli-plugin (89 stars, last pushed 15d ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,323 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to cursor-delegate, differing in 21 lines, and is treated as a copy.
Other agents, from other repositories
index
Agent "index" from pivanov/agents-wire, covering agents, model selection by agent, live model list (cursor and opencode), detect what's available and install table.
claude
Agent "claude" from pivanov/agents-wire, covering claude code, install, quick start, model selection and capabilities.
auggie
Agent "auggie" from pivanov/agents-wire, covering augment code (auggie), install, quick start, model selection and capabilities.
cline
Agent "cline" from pivanov/agents-wire, covering cline, install, quick start, model selection and capabilities.
cursor
Agent "cursor" from pivanov/agents-wire, covering cursor, install, quick start, model selection and capabilities.
kilo
Agent "kilo" from pivanov/agents-wire, covering kilo, install, or: export kiloapikey="your-api-key", quick start and model selection.