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/verbalize-public/open-delegate/ode-delegatenpx skills add Verbalize-public/open-delegate --skill ode-delegategit clone --depth 1 https://github.com/Verbalize-public/open-delegateWhat 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 | $0.00075 | $0.01302 |
| Opus 5 | $0.00037 | $0.00651 |
| Sonnet 5 | $0.00015 | $0.00260 |
| Haiku 4.5 | $0.00007 | $0.00130 |
Grade A, and why
ode-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 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCode delegate (cost-first)
Bridge to a real opencode serve process. Goal: reduce Cursor spend by handing
work to cheaper OpenCode alternatives (Zen free, open-weights, mid/cheap OpenRouter).
Not a place to chase Anthropic/OpenAI flagships — see reference/models.md.
When to use this vs native Task
| Need | Use |
|---|---|
Model is on ODE_MODELS (cheap force catalog) or is already openrouter/… |
ode_delegate + ode_await (see soft rule open-delegate-routing) |
| Cursor-native model, not on ODE_MODELS | Native Task / subagent |
| Unattended background / isolated OpenCode session | ode_delegate |
Pass OpenCode provider/model ids as-is. Do not invent Cursor-slug remaps.
Tool selection
| Step | Tool |
|---|---|
| Start / resume | ode_delegate → { sessionId, status, previewUrl?, answer? } — omit sessionId to create; pass sessionId to resume a finished session. Optional waitMs blocks until done (one-call short tasks). |
| Wait / peek | ode_await (default 30s; timeoutMs: 0 = single non-blocking check; "running"/"starting" = call again) |
| Read history | ode_transcript |
| Stop | ode_cancel |
| Diagnose | ode_diagnostics (no input; bridge pid/logs, live runtimes, recent events) |
Contracts: reference/tools.md.
Core loop
- Pick a cheap OpenCode id (or omit
modelforOPEN_DELEGATE_DEFAULT_MODEL/ OpenCode default). ode_delegate({ prompt, model?, agent?, cwd?, title?, waitMs? }). Prompt is capped at ~512KiB inline — for anything larger, write it to a file and passpromptPathinstead (promptandpromptPathare mutually exclusive).- If you did not pass
waitMs(or it timed out still running):ode_await({ sessionId, timeoutMs? })until"done"/"error"/"cancelled"(treat"starting"like"running"— just call again). When status is still running andcurrentActivityis present, narrate it briefly before the next await. - On
"error", readerrorMessage/errorCode(reference/errors.md). - On
"done", prefer the cappedanswerfield; if missing/empty when text was expected →ode_transcript({ includeToolCalls: true }), thenode_delegate({ sessionId, prompt })with a “write the answer” nudge. - Need full history?
ode_transcript({ sessionId }).
What ships with it
4 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.
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 · 106 lines · 75 tokens per session scan A 1ccf3100f0fc
ode-delegate is a skill published in the GitHub repository Verbalize-public/open-delegate (1 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,302 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…