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/shrekshrek/project-workflowWrote 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/shrekshrek/project-workflow/marketplace)<a href="https://agentmods.dev/plugins/shrekshrek/project-workflow/marketplace"><img src="https://agentmods.dev/badge/plugins/shrekshrek/project-workflow/marketplace/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/shrekshrek/project-workflow/marketplace"><img src="https://agentmods.dev/badge/plugins/shrekshrek/project-workflow/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
project-workflow marketplace 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.
What it actually says
{
"name": "project-workflow",
"owner": {
"name": "shrek.wang"
},
"metadata": {
"description": "project-workflow v3 — spec-driven feature development blueprint for AI-assisted coding"
},
"plugins": [
{
"name": "project-workflow",
"source": {
"source": "git-subdir",
"url": "https://github.com/shrekshrek/project-workflow.git",
"path": "claude/project-workflow",
"ref": "plugin-dist"
},
"description": "Spec-driven feature development plugin (Claude Code-native). 9 skills (/project-init, /project-personalize, /feature-init, /spec-quality-check, /spec-revise, /feature-done, /feature-archive, /spec-reconcile, /agents-md-revise) + 6 sub-agents (agents-md-reviewer, spec-reviewer, spec-quality-reviewer, tech-researcher, codebase-explorer, decision-completeness-auditor).",
"author": {
"name": "shrek.wang"
},
"homepage": "https://github.com/shrekshrek/project-workflow",
"repository": "https://github.com/shrekshrek/project-workflow",
"license": "MIT",
"keywords": ["spec-driven", "workflow", "blueprint", "agents-md"],
"category": "workflow"
}
]
}
The plugins it lists here
This marketplace lists 1 plugin kept in the same repository. Each has its own page, its own measurements and its own install command.
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 · 30 lines scan A 0199a35d690e
project-workflow marketplace is a plugin published in the GitHub repository shrekshrek/project-workflow (2 stars, last pushed 3d 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
specmanager
Lifecycle kanban for Claude Code projects (PRD → architecture → plan → tasks → walkthroughs).
hippo
hippocampus — perception and memory for coding agents: task registry, outcome ledger, and background clerks that turn transcripts into evidence. Records; never enforces. CLI and slash commands are hippo.
crew
A multi-agent dev harness: hand it a goal and the orchestrator triages, implements, reviews, responds to feedback, and keeps docs and knowledge current — autonomously, up to a review-ready PR. Use the individual skills directly, or /crew:run to let it decide what to do.
devforge-ai
Enterprise & Startup SDLC orchestration plugin: 10 agents across 5 phases (Plan, Build, Verify, Ship, Operate), 43 knowledge skills, 16 commands. Hyper-scale RCA, 7-tier test matrix, Stripe monetization, and dynamic autonomous routing.
manager
Product and project management discipline for the NVZver marketplace. Agents: product-manager — shapes vague ideas into structured draft pitches and returns their full content + pending human gates (writes no files); project-manager — stewards the roadmap, recommends what to build next with dependency/risk/value…
yonsei-rms
Summarize supplied RMS project data and audit its budget arithmetic or participant roles and periods without uploads, approvals, or submissions.