A coding worker for difficult, multi-step engineering tasks and problems that cross several parts of a project.

Use it for architecture changes, cross-component work, ambiguous tasks, concurrency issues, and other problems needing careful verification.

It is intended for work where simple edits are not enough, such as unclear requirements, concurrency, or complex debugging.

How Noizefield/audio-plugin-coder configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Noizefield/audio-plugin-coder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Noizefield/audio-plugin-coder/main/.agents/agents/deep-worker.md

Clone the repo

git clone --depth 1 https://github.com/Noizefield/audio-plugin-coder

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/noizefield/audio-plugin-coder/deep-worker/github.svg)](https://agentmods.dev/agents/noizefield/audio-plugin-coder/deep-worker)

Your own site

<a href="https://agentmods.dev/agents/noizefield/audio-plugin-coder/deep-worker"><img src="https://agentmods.dev/badge/agents/noizefield/audio-plugin-coder/deep-worker/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/noizefield/audio-plugin-coder/deep-worker"><img src="https://agentmods.dev/badge/agents/noizefield/audio-plugin-coder/deep-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 78 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00029	$0.00078
Opus 5.5	$0.00012	$0.00031
Sonnet 5.5	$0.00006	$0.00016
Haiku 4.5	$0.00003	$0.00008

Measured 28d ago against content hash eb1d431e4194, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 28d 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.

.agents/agents/deep-worker.md · 11 lines

What it actually says

Handle difficult multi-step work, architecture, ambiguous problems, complex debugging, concurrency and cross-component changes.

Use strong verification. Recommend escalation only when the problem remains unresolved or clearly warrants the highest-capability 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.

28d ago First seen · 11 lines · 29 tokens per session scan A eb1d431e4194

Subscribe to this mod's changes

deep-worker is an agent published in the GitHub repository Noizefield/audio-plugin-coder (354 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 78 once invoked, about $0.0001 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 2026-10-10.

Building agents Debugging

deep-worker next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
deep-workerNoizefield/audio-plugin-coder	Agent	354	4d ago	MIT	A	29	Claude Code
review-obsidian-guidelinesuphy/obsidian-reminder	Agent	662	yesterday	MIT	A	63	Claude Code
debuggerTT-Wang/forge	Agent	35	3d ago	MIT	A	17	Claude Code
debuggerbostonaholic/rpikit	Agent	20	4d ago	MIT	A	28	Claude Code
loom-advisorcosmix/loom	Agent	65	5d ago	MIT	A	53	Claude Code
evolve-retrospectivemickeyyaya/evolve-loop	Agent	6	today	Apache-2.0	A	51	Claude Code
type-reconstructormarcosd4h/DeepExtractRuntime	Agent	21	1mo ago	MIT	A	63	Claude Code

audio-plugin-coder: Agent for Claude Code