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/pivanov/agents-wire/opencodegit clone --depth 1 https://github.com/pivanov/agents-wireWhat 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 | $0.00509 |
| Opus 5 | $0.00000 | $0.00254 |
| Sonnet 5 | $0.00000 | $0.00102 |
| Haiku 4.5 | $0.00000 | $0.00051 |
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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCode
Agent ID: opencode
OpenCode speaks ACP natively via opencode acp - no bridge package needed.
Install
npm install -g opencode-ai
Configure your provider API key according to the OpenCode docs.
Quick Start
import { agents } from "@pivanov/agents-wire";
const result = await agents.ask(
"opencode",
"Refactor src/auth.ts",
{
permission: "auto-allow",
},
);
console.log(result.text);
Model Selection
opencode acp does not advertise a --model flag (verified via --help). options.model
is forwarded as ACP modelPreference but is currently silently ignored by opencode acp.
To list the models OpenCode supports at runtime, call listAvailableModels():
import { definitionFor } from "@pivanov/agents-wire/catalog";
const def = definitionFor("opencode");
const models = (await def.listAvailableModels?.()) ?? def.models ?? [];
// models is IAgentModelOption[] - falls back to static list on any failure
console.log(models.map((m) => m.id));
Configure the active model via the OpenCode configuration (e.g. opencode auth login).
options.effort is sent via ACP setSessionConfigOption (best-effort); whether OpenCode
honors it depends on the installed version.
Capabilities
| Feature | Supported |
|---|---|
ask / stream / session |
✅ |
askJson |
✅ |
| MCP stdio | ✅ |
| MCP http/sse | ✅ |
Session listing (listSessions) |
✅ |
| Tool call interception | ✅ |
Cost Tracking
OpenCode reports per-turn costUsd depending on the provider configured. Full cost tracking and maxCostUsd budget enforcement work when the underlying provider reports costs.
Auth Failure Detection
If the configured provider API key is missing or invalid, the SDK catches the authentication-failure pattern in stderr and throws AgentUnauthenticatedError.
Gotchas
- OpenCode is provider-agnostic - configure your provider (Anthropic, OpenAI, etc.) before use.
- Cost reporting depends on the provider; not all providers expose per-turn cost data.
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 · 75 lines · 0 tokens per session scan A 8ea7ea0594ee
opencode is an agent published in the GitHub repository pivanov/agents-wire (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 509 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 agents, from other repositories
codex-execute
Implement a SPECIFIC, well-defined plan or plan-step with Codex. Use ONLY when the user has a written plan, plan-step, named files, or acceptance criteria to execute ("execute this via codex", "implement this plan", "/codex:execute", or a --plan file is in context). Do NOT use when the user is stuck/exploring (use…
cursor-delegate
Delegate a SPECIFIC, well-defined implementation task or plan step to Cursor in agent mode on the Auto model. Cursor is the fast lane for mechanical writing — long file writes (200+ lines), pattern-following across many files, bulk refactors. Supports autonomous multi-step runs via --until-done. Pair with…
cursor-research
Delegate read-only EXTERNAL web/documentation research to Cursor. Use when the user wants current library/API/docs research, "what's the current way to…", or to compare approaches — and you'd rather not spend Claude's context on web reading. Cursor runs read-only (ask mode) with web search + fetch and returns findings…
opencode-research
Delegate read-only EXTERNAL web/documentation research to OpenCode. Use when the user wants current library/API/docs research, "what's the current way to…", or to compare approaches — and you'd rather not spend Claude's context on web reading. OpenCode runs read-only (ask mode) with web search + fetch and returns…
codex-rescue
Hand an OPEN-ENDED or stuck problem to Codex for independent investigation. Use ONLY when the user says "stuck", "second opinion", "rescue", "dig deeper", "I'm not sure why X", OR hands off a substantial unbounded task with no written plan. Do NOT use when a plan or plan-step file is in context (use codex-execute) or…
cursor-explore
Delegate quick read-only CODEBASE exploration to Cursor. Use to answer questions about the current repository ("where is X handled?", "how does Y flow?", "summarize the adapter layer") without spending Claude's tokens reading files. Cursor runs read-only (ask mode) using semantic search, grep, and its Explore…