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.
/plugin marketplace add pwdev-solucoes/pwdev-claude-marketplacenpx agentmods add plugins/pwdev-solucoes/pwdev-claude-marketplace/pwdev-flowgit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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/pwdev-solucoes/pwdev-claude-marketplace/pwdev-flow)<a href="https://agentmods.dev/plugins/pwdev-solucoes/pwdev-claude-marketplace/pwdev-flow"><img src="https://agentmods.dev/badge/plugins/pwdev-solucoes/pwdev-claude-marketplace/pwdev-flow.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
pwdev-flow 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 yesterday.
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": "pwdev-flow",
"displayName": "PWDEV Flow — Portable Spec-Driven Development",
"version": "0.6.0",
"description": "Portable, approval-gated software development for Claude Code and Codex, with shared artifacts, semantic audit, guarded delegation, and isolated native fleets.",
"author": {
"name": "Paulo Soares",
"url": "https://github.com/soarescbm"
},
"homepage": "https://github.com/pwdev-solucoes/pwdev-claude-marketplace",
"repository": "https://github.com/pwdev-solucoes/pwdev-claude-marketplace",
"license": "Apache-2.0",
"keywords": [
"claude-code",
"claude-plugin",
"codex",
"workflow",
"spec-driven",
"audit",
"fleet",
"delegation",
"portable"
]
}
What it installs
The manifest is a name and a version. 17 skills, 1 command travel with it, and installing the plugin installs all of them — 821 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill flow-fleet A 59 tokens
- Skill flow-delegate A 53 tokens
- Skill flow-init A 51 tokens
- Skill flow-compat A 52 tokens
- Skill flow-audit A 52 tokens
- Skill flow-design A 41 tokens
- Skill flow-discover A 39 tokens
- Skill flow-execute A 45 tokens
- Skill flow-health A 42 tokens
- Skill flow-maintenance A 47 tokens
- Skill flow-product A 47 tokens
- Skill flow-quick A 48 tokens
- Skill flow-review A 48 tokens
- Skill flow-simplify A 47 tokens
- Skill flow-verify A 45 tokens
- Skill flow-memory A 50 tokens
- Skill flow-plan A 45 tokens
- Command compat A 10 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.
- yesterday First seen · 25 lines scan A e52573fd7422
pwdev-flow is a plugin published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 15d ago), licensed Apache-2.0. 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 2026-09-03.
Other plugins, from other repositories
milestone-driver
Drives a GitHub milestone to completion: triages each issue for design gaps + dependency order up front, then for each buildable issue finds the root cause (or parks it), dispatches a TDD implementer subagent, runs unit + E2E tests + code review, opens a PR, and auto-merges issues on CI green. The whole loop sits…
rook-maintainer
Maintainer-grade skills for rook (github.com/rook/): code review, backlog triage, systemic-PR campaigns, and the rook house conventions they enforce.
obw
Obsidian Workspace — project-scoped vault productivity (capture / notes / PM). Skills-only: owns folder layout and templates; runs the Obsidian CLI directly via the official obsidian-cli skill.
feishu-calendar
Manage Feishu (Lark) calendar events — create, read, update, delete events and manage attendees via the Feishu Open Platform Calendar API v4.
gse
GSE-One — AI engineering companion for structured SDLC management. 24 commands, adaptive risk analysis, unified backlog, knowledge transfer, worktree isolation.
product-management
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.