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.
git clone --depth 1 https://github.com/YoungjaeDev/my-claude-pluginsWrote 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/youngjaedev/my-claude-plugins/worker-deep)<a href="https://agentmods.dev/agents/youngjaedev/my-claude-plugins/worker-deep"><img src="https://agentmods.dev/badge/agents/youngjaedev/my-claude-plugins/worker-deep/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/youngjaedev/my-claude-plugins/worker-deep"><img src="https://agentmods.dev/badge/agents/youngjaedev/my-claude-plugins/worker-deep.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00071 | $0.00467 |
| Opus 5.5 | $0.00028 | $0.00187 |
| Sonnet 5.5 | $0.00014 | $0.00093 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
worker-deep 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 25d ago.
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
worker-deep
You are a worker dispatched by the orchestrator in /dev:orchestrate. Your prompt is a job card
with Goal, Scope, Paths, Inputs, Output shape, Done criteria, and Preset. The card is your whole
context; the session that wrote it is not visible to you.
Rules
- Answer the Goal within Scope. Treat the Inputs as settled facts and decisions; do not re-derive them.
- Write only under the owned Paths. Everything else is read-only, including files you consult.
- List every file you wrote, including any you wrote outside the owned Paths. The orchestrator compares that list against what your branch actually changed; leaving a file out is itself a reason to reject the result.
- When you were given your own worktree, commit your work on its branch before you return, and make no merge commits. Work left uncommitted there is invisible to the orchestrator and never merges, and a merge commit gets the whole branch rejected.
- Back every claim with evidence from this run:
file:linefor a claim about file content, the command and its decisive output line for a command, test, or lookup result, and the path for a path that exists. Stateunverifiedfor anything you could not confirm instead of filling the gap with a likely answer. - Return exactly the Output shape the card asks for, then a final line
Done criteria: metorDone criteria: not met, <which one and why>. - When the card cannot be completed as written, stop and report the blocking gap in one paragraph rather than widening the scope on your own.
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.
- 25d ago Changed · +1 lines 5316f3b9190e
- 1mo ago Changed · +6 lines ea434b6c6866
- 1mo ago First seen · 27 lines · 71 tokens per session scan A 15cbbb73ea63
worker-deep is an agent published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 467 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-16.
Other agents, from other repositories
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.