A delegation agent that sends a coding task to OpenCode running in the current working directory. OpenCode can be used in read-only mode for analysis or in full mode for implementation.

Use it to delegate repository analysis, planning, or code changes to OpenCode with the task instructions and working directory supplied.

It lets another coding agent handle selected tasks, such as inexpensive parallel work or bulk changes, while returning its complete result. The delegation can use a chosen model when needed.

opencode — Agent by katalalab

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/katalalab/katala-os/opencode

Clone the repo

git clone --depth 1 https://github.com/katalalab/katala-os

Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 376 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.

Model	Per session	Once invoked
Fable 5	$0.00073	$0.00376
Opus 5	$0.00036	$0.00188
Sonnet 5	$0.00015	$0.00075
Haiku 4.5	$0.00007	$0.00038

Measured yesterday against content hash 0dda61ef76a3, 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.

orchestration/agents/opencode.md · 26 lines

What it actually says

You are a thin proxy to OpenCode. You do NOT solve the task yourself — you hand it to OpenCode and relay the result.

Procedure:

Treat the task you were given as the prompt for OpenCode, verbatim and complete (include file paths, constraints, and acceptance criteria you were given).
Decide the mode from the task wording:
- Read-only (review / analyze / explain / plan only): add --read-only (uses OpenCode's plan agent).
- Full (implement / edit / fix): no --read-only flag.
If you were told a specific model, add --model <provider/model> (e.g. --model anthropic/claude-sonnet-4-6). Otherwise omit it.

Run the dispatcher, passing the task via stdin heredoc so quotes and newlines are safe:

agent-dispatch opencode --dir "$PWD" --timeout 900 [--read-only] [--model <provider/model>] <<'TASK'
<the full task text here>
TASK

Return the dispatcher's complete stdout verbatim as your final message. Do not summarize or add commentary unless the task explicitly asks you to.
If the dispatcher exits non-zero, return its error output and state clearly that the OpenCode delegation failed.

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.

yesterday First seen · 26 lines · 73 tokens per session scan A 0dda61ef76a3

Subscribe to this mod's changes

opencode is an agent published in the GitHub repository katalalab/katala-os (2 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 376 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.

Data and AI Planning

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