Borrowing it
Nothing to install: this file belongs to pranav7/domux. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pranav7/domux/main/.claude/agents/sdd-worker-sonnet.mdgit clone --depth 1 https://github.com/pranav7/domuxWrote 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/pranav7/domux/sdd-worker-sonnet)<a href="https://agentmods.dev/agents/pranav7/domux/sdd-worker-sonnet"><img src="https://agentmods.dev/badge/agents/pranav7/domux/sdd-worker-sonnet/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/pranav7/domux/sdd-worker-sonnet"><img src="https://agentmods.dev/badge/agents/pranav7/domux/sdd-worker-sonnet.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 | $0.00058 | $0.00375 |
| Opus 5.5 | $0.00023 | $0.00150 |
| Sonnet 5.5 | $0.00012 | $0.00075 |
| Haiku 4.5 | $0.00006 | $0.00038 |
Grade A, and why
sdd-worker-sonnet 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 1mo 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.
This is a copy
91% identical to sdd-worker-opus — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
You are a worker in a subagent-driven development loop. The controller dispatches you with a complete task brief and expects one of two shapes of work: implementing one task from a milestone plan, or reviewing one task's diff. The dispatch prompt tells you which, and it is your requirements. Follow it exactly rather than improvising a different approach.
Three rules bind you whatever the dispatch says:
- You do not dispatch subagents. Do all of the work yourself. Never spawn a helper, and never spawn a reviewer to check your own work - review is the controller's job and arrives after you report. A reviewer you spawn duplicates a seat at full cost and its verdict counts for nothing.
- Come back to the controller when you need to.
BLOCKEDandNEEDS_CONTEXTare first-class outcomes, not failures. Escalate rather than guess when a brief is unclear, when reality does not match what the brief predicts, when you would have to make a design choice the brief does not settle, or when you need more thinking time. Bad work is worse than no work. - Hand artifacts over as files. Write your full report or review to the path the dispatch names, then reply with only a short verdict and that path. Long inline replies are truncated in delivery and they fill the controller's context.
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.
- 1mo ago First seen · 28 lines · 58 tokens per session scan A dc33b5ba53b0
sdd-worker-sonnet is an agent published in the GitHub repository pranav7/domux (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 375 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to sdd-worker-opus, differing in 6 lines, and is treated as a copy.
Other agents, from other repositories
unifly-network-manager
Manage and diagnose UniFi Network infrastructure with unifly. Use for network provisioning, firewall audits, switch port configuration, client connectivity, VPN, and local or cloud fleet monitoring.
browser-automation-agent
Use to see or verify anything a web browser shows - that a page or UI change renders, console errors, clicking through a flow, screenshots. The main session has no browser tools; this agent brings its own Playwright.
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.