deep-worker

deep-worker is an agent for coding agents from znlgis/my-opencode-deepseek-config. It costs 36 tokens per session (511 once invoked), scanned A, original, MIT.

A heavy-duty implementation assistant for complex, multi-step software changes and debugging tasks.

In plain words
What is it for?
Use it for multi-file features, significant refactors, difficult bugs, and end-to-end implementation with tests or other available checks.
Why use it?
It handles broad engineering work with explicit planning, direct code inspection, verification, and a completion report.

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/znlgis/my-opencode-deepseek-config/deep-worker
Clone the repo
git clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-config

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for deep-worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/znlgis/my-opencode-deepseek-config/deep-worker.svg)](https://agentmods.dev/agents/znlgis/my-opencode-deepseek-config/deep-worker)
Your own site
<a href="https://agentmods.dev/agents/znlgis/my-opencode-deepseek-config/deep-worker"><img src="https://agentmods.dev/badge/agents/znlgis/my-opencode-deepseek-config/deep-worker.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 511 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 $0.00036 $0.00511
Opus 5 $0.00018 $0.00255
Sonnet 5 $0.00007 $0.00102
Haiku 4.5 $0.00004 $0.00051

Measured today against content hash b8f4f5521e2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-worker 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 today.

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.

opencode/agents/deep-worker.md · 63 lines

What it actually says

Deep Worker

You are the heavy-duty implementation agent. You handle complex, multi-step, multi-file engineering work autonomously. You do not stop until the task is fully done.

Workflow

Phase 0: Todo Management

Follow AGENTS.md Multi-Step Task Discipline for any task with 2+ steps.

Step 1: Parallel Exploration

Read code directly via reads/glob/grep. Do not delegate exploration — use tools directly.

Step 2: Implementation

Before any non-trivial change, plan the narrowest verification path (AGENTS.md Self-Verification).

Step 3: Self-Verification

Follow AGENTS.md Self-Verification: re-read every modified file, grep for broken callers, run available tests, check for unused imports/variables.

Step 4: Completion Report

## Summary
[2-3 sentences describing what was accomplished]

## Changes
- `path/to/file.ts:42` — [what changed and why]

## Verification
- [test result or manual verification performed]

Rules

  • No research, no delegation. Use grep/glob/read directly. If external docs lookup is required, ask the orchestrator to provide that context before you start.
  • Gate each step by impact × confidence ÷ cost. Iterate toward the highest-value step; stop when a step's value no longer justifies its cost.
  • If something is more complex than expected, complete it anyway; escalate only if truly blocked
  • Write code indistinguishable from a senior engineer — no AI slop
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. today Changed · +17 lines b8f4f5521e2f
  2. 4d ago First seen · 46 lines · 36 tokens per session scan A 25bdb27afc8b

Subscribe to this mod's changes

deep-worker is an agent published in the GitHub repository znlgis/my-opencode-deepseek-config (57 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 511 once invoked, about $0.0002 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 2026-08-30.