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/PrabhdeepSingh/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/plugins/prabhdeepsingh/claude-plugins/sonu)<a href="https://agentmods.dev/plugins/prabhdeepsingh/claude-plugins/sonu"><img src="https://agentmods.dev/badge/plugins/prabhdeepsingh/claude-plugins/sonu/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/plugins/prabhdeepsingh/claude-plugins/sonu"><img src="https://agentmods.dev/badge/plugins/prabhdeepsingh/claude-plugins/sonu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sonu 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
89% identical to prabhdeep-tools marketplace — 150 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "sonu",
"version": "4.10.0",
"description": "Make your coding agent work like a senior teammate instead of an eager intern. /sonu:build writes every change in your style and test-first, then hands it back with the riskiest parts flagged before you review. /sonu:ship takes it from working tree to merged PR on its own — collecting every AI reviewer bot enabled on the repo, fixing or answering each finding, looping until clean. Once you trust that loop, /sonu:factory turns your issue tracker into the queue: label a ticket in GitHub Issues, Jira, Linear, or a dependency-free local Markdown store, and the agent specs it, builds it in its own git worktree so several tickets can run in parallel, and — once you review the diff and apply the ship label — takes it through review to a merged PR, reporting plan, progress, and risks back to the ticket the whole way. Run a pass per label, or let /sonu:factory poll watch the queue for you. You approve the spec, the diff, and the ship — nothing merges without your label. It also knows what a good interface looks like: /sonu:interface-review audits a whole screen or flow across accessibility, layout, typography, color, motion, and copy, and those same bars fire automatically while it builds. The discipline lives in 26 skills that auto-apply as it works, and that you can read and edit like any other file: code-standards, tdd, debugging, security, performance, intent-interview, design-tree, model-tiering, self-review, blast-radius, pr-conventions, safe-migrations, infra-standards, observability, seo, interface-review, accessibility, layout, ui-polish, typography, colors, ux-writing, ticket-lifecycle, ticket-triage, classify-tickets, bug-finder. Every skill is plain Markdown you can read, fork, and edit — no runtime, no service to sign up for. Works in Claude Code and Cursor. The local tracker needs nothing but git; GitHub Issues uses the gh CLI, and Jira and Linear use their MCP servers or your own API credentials.",
What it installs
The manifest is a name and a version. 26 skills, 3 commands travel with it, and installing the plugin installs all of them — 2,804 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill code-standards A 81 tokens
- Skill design-tree A 62 tokens
- Skill self-review A 79 tokens
- Skill ticket-lifecycle A 105 tokens
- Skill tdd A 80 tokens
- Skill pr-conventions A 80 tokens
- Skill infra-standards A 106 tokens
- Skill model-tiering A 93 tokens
- Skill colors A 99 tokens
- Skill observability A 88 tokens
- Skill safe-migrations A 100 tokens
- Skill ux-writing A 95 tokens
- Skill performance A 99 tokens
- Skill seo A 114 tokens
- Skill debugging A 100 tokens
- Skill accessibility A 107 tokens
- Skill blast-radius A 96 tokens
- Skill security A 102 tokens
- Skill ticket-triage A 114 tokens
- Skill ui-polish A 109 tokens
- Skill layout A 104 tokens
- Skill bug-finder A 94 tokens
- Skill classify-tickets A 101 tokens
- Skill interface-review A 96 tokens
- Skill intent-interview A 98 tokens
- Skill typography A 103 tokens
- Command ship A 86 tokens
- Command factory A 108 tokens
- Command build A 105 tokens
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 Changed e3d79944a82c
- 1mo ago Changed 11825a86d410
- 1mo ago Changed cc2a34403647
- 1mo ago Changed 9a893f629e7d
- 1mo ago First seen · 78 lines scan A 30688e1a8f6d
sonu is a plugin published in the GitHub repository PrabhdeepSingh/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. It is 89% identical to prabhdeep-tools marketplace, differing in 150 lines, and is treated as a copy.
Other plugins, from other repositories
branch-recap
Tells you what your branch actually changed — what was done, why, and what deserves a second look, instead of the diff — then files the fixes into the commits they belong to.
odin-git
ODIN workflows for commits, branches, pull requests, review feedback, and issue tracking.
issue-to-pr
Take a GitHub issue (bare, or tracked on a Project board) from triage to a merge-ready PR through a gated, worktree-isolated pipeline that scales its depth to the task and asks at most one batched question. The gates hold every run: design hardening, tests green, code review clean. Once you approve the PR in-session…
agent-dispatch
Start issue-to-pr runs from GitHub labels on your own machine: a scheduled tick picks the issue you labelled agent, or the one you replied on, and runs it headless under your own Claude Code or Codex login, on Windows, macOS or Linux.
review-pr
Review PRs in a Tour Guide (expository) or Adversarial (audit) posture, with logical file ordering, context, and severity-rated findings. Forge-agnostic (GitHub + Bitbucket).
python-dev
Python development workflow with architecture design, coding guidelines, testing patterns, and specialized review agents.