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/znlgis/my-opencode-deepseek-config/deep-workergit clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-configWrote 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.
[](https://agentmods.dev/agents/znlgis/my-opencode-deepseek-config/deep-worker)<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>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 | $0.00036 | $0.00511 |
| Opus 5 | $0.00018 | $0.00255 |
| Sonnet 5 | $0.00007 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
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.
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
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.
- today Changed · +17 lines b8f4f5521e2f
- 4d ago First seen · 46 lines · 36 tokens per session scan A 25bdb27afc8b
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.
Other agents, from other repositories
human-review
Evaluate PR seams for splitting and distill business value, design decisions, abandoned ideas, and risk from the changeset.
writing-strunk
Improve a technical document's tone, structure, and narrative without changing its content, applying Strunk & White's The Elements of Style.
ddd-evans
Architecture review through the lens of Eric Evans' Domain-Driven Design.
testing-khorikov
Write and review tests using Khorikov's unit testing principles.
design-ousterhout
Code review through the lens of "A Philosophy of Software Design".
playwright
Browser automation and web interaction using Playwright.