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/ihudak/ihudak-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/ihudak/ihudak-claude-plugins/dev-workflows)<a href="https://agentmods.dev/plugins/ihudak/ihudak-claude-plugins/dev-workflows"><img src="https://agentmods.dev/badge/plugins/ihudak/ihudak-claude-plugins/dev-workflows/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/ihudak/ihudak-claude-plugins/dev-workflows"><img src="https://agentmods.dev/badge/plugins/ihudak/ihudak-claude-plugins/dev-workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dev-workflows 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 23d 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
{
"name": "dev-workflows",
"version": "4.2.3",
"description": "Five slash commands for the implementation half of the product lifecycle: `/design` turns a specification into a design, with Opus review and an optional three-take fan-out on a contested interface. `/implement` builds it, gated by Opus plan critique and code review before tests. `/ready` verifies an ARD/spec/design chain's readiness, read-only, no tracker read. `/upgrade` plans and executes dependency upgrades; `/vuln` researches and fixes a CVE. Twelve subagents, one hook, fifteen reference files, no bundled skill. Every code-changing command commits before the run ends; push and PR sit behind one consent choice. Depends on the companion `workflows-core` plugin for its shared foundation. The product-definition ladder, `/epics`, and the BRD-to-PRD route now ship in `product-workflows`; documentation commands ship in `docs-workflows`. Neither is a dependency.",
"author": {
"name": "Ivan Gudak",
"email": "[email protected]"
},
"homepage": "https://github.com/ihudak/ihudak-claude-plugins/tree/main/plugins/dev-workflows",
"repository": "https://github.com/ihudak/ihudak-claude-plugins",
"license": "MIT",
"dependencies": [
"workflows-core"
],
"keywords": [
"implement",
"design",
"ready",
"vuln",
"upgrade",
"development",
"workflow",
"security",
"dependencies",
"value-increment"
]
}
What it installs
The manifest is a name and a version. 5 commands, 12 agents, 1 hook travel with it, and installing the plugin installs all of them — 1,416 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command implement A 48 tokens
- Command vuln A 38 tokens
- Command design A 110 tokens
- Command upgrade A 41 tokens
- Command ready C 127 tokens
- Agent test-baseliner A 93 tokens
- Agent code-review A 58 tokens
- Agent risk-planner A 44 tokens
- Agent test-writer A 98 tokens
- Agent design-reviewer A 87 tokens
- Agent interface-designer A 85 tokens
- Agent review-fixer A 43 tokens
- Agent vuln-fixer A 122 tokens
- Agent upgrade-executor A 116 tokens
- Agent upgrade-planner A 97 tokens
- Agent vuln-research A 121 tokens
- Agent readiness-reviewer C 88 tokens
- Hook UserPromptSubmit A not measured
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.
- 23d ago Changed 28e5262fc7b6
- 24d ago Changed 3d83fb7caeb0
- 28d ago Changed a1340a8d9598
- 1mo ago Changed a97da3643304
- 1mo ago Changed · -1 lines 419e18a7ffa9
- 1mo ago Changed · +1 lines 1f549d5d6ca1
- 1mo ago First seen · 28 lines scan A 71913ec0b829
dev-workflows is a plugin published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 24d 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
review-gate
Native Claude Code AI code review + blocking pre-push gate on your Claude subscription. Isolated headless reviewer, severity/confidence verdicts, fails closed. open-code-review, done compliantly.
handbook-agent-spec-kit
Spec-driven development workflow system with structured phases: Requirements → Design → Tasks → Implementation.
sound
Code taste as installable rules. Probe a repo's stack, select only the rules its code shows a surface for (evidence-cited per rule), confirm, and scaffold a browsable .claude/sound/ rule map (surfaced by the sound:prime skill). Installed rules are user-owned; re-runs reconcile.
smk marketplace
Plugin marketplace listing 13 plugins: cursor-delegate, spring-clean, portal-skills, readable, decode.
jira-pack
Issue-tracker pack: /jira-fix takes a ticket link of any type, verifies tracker access, classifies it as a defect or a change, reproduces the defect or writes a failing acceptance test for the change, routes the work to core executors, comments back with evidence and moves the ticket to the QA column. Opt-in; requires.
mem-rescue
Diagnose and fix memory pressure (full swap, crashing browser tabs) in one or two commands. macOS first, Linux best-effort. Agent-agnostic SKILL.md plus two bundled scripts.