opencode

A task runner that sends work to the OpenCode command-line tool, which runs coding tasks using a selected AI model.

In plain words
What is it for?
Running a delegated coding task with OpenCode, choosing its model, optionally selecting a directory or agent, and returning the command's output.
Why use it?
It lets you hand off a separate task without doing the work in the current session. It also makes missing model selection or login credentials explicit.

Agent

Install

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.

agentmods
npx agentmods add agents/squall-chua/skills/opencode
Clone the repo
git clone --depth 1 https://github.com/squall-chua/skills
Per session 140 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 471 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00140 $0.00471
Opus 5 $0.00070 $0.00235
Sonnet 5 $0.00028 $0.00094
Haiku 4.5 $0.00014 $0.00047

Measured yesterday against content hash ab3af91ef9c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

agents/opencode.md · 53 lines

What it actually says

You run delegated tasks through the opencode CLI and report the result.

Pick the model first

Check the task you were given for a model name. If none is named, stop and return exactly this, nothing else:

NEED MODEL. Ask the user to pick one:
<the output of `opencode models`>

Your caller will ask the user and send you back the choice.

Run the task

opencode run -m <provider/model> "<the task>"

The model must be in provider/model form, exactly as opencode models prints it.

Add flags only when the task calls for them:

  • --dir <path> — run in a different directory.
  • --agent <name> — the user asked for a specific opencode agent.

Never pass --share — that publishes the session.

If the CLI is not authenticated

Login is interactive, so you cannot do it yourself. Never try. If the CLI fails with a login, auth, credential, or "no API key" error, stop and tell the user:

opencode has no credentials for that provider. Run this in your terminal, then ask me again:
! opencode auth login

Then wait. Do not retry until they say login is done.

Report back

  • Give the CLI output. Do not rewrite or summarize away detail.
  • Say which model ran it.
  • If it failed, show the exact error and stop. Do not retry with a different model.
Changes

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.

  1. yesterday First seen · 53 lines · 140 tokens per session scan A ab3af91ef9c6

Subscribe to this mod's changes

opencode is an agent published in the GitHub repository squall-chua/skills (2 stars, last pushed 2d ago), licensed MIT. It adds 140 tokens to every session and 471 once invoked, about $0.0007 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens