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/XRenSiu/claude-code-forgeWrote 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/xrensiu/claude-code-forge/pdforge)<a href="https://agentmods.dev/plugins/xrensiu/claude-code-forge/pdforge"><img src="https://agentmods.dev/badge/plugins/xrensiu/claude-code-forge/pdforge/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/xrensiu/claude-code-forge/pdforge"><img src="https://agentmods.dev/badge/plugins/xrensiu/claude-code-forge/pdforge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pdforge 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": "pdforge",
"description": "Product Development Forge - AI-driven 7-phase product development workflow. Provides complete methodology from requirements analysis to deployment, including brainstorming, TDD, three-stage review, and auto-fix loops.",
"version": "1.14.0",
"author": {
"name": "XRenSiu",
"email": "[email protected]"
},
"homepage": "https://github.com/XRenSiu/claude-code-forge/tree/main/plugins/pdforge",
"repository": "https://github.com/XRenSiu/claude-code-forge",
"license": "MIT",
"keywords": [
"product-development",
"tdd",
"code-review",
"brainstorming",
"workflow",
"automation",
"figma",
"design-to-code"
]
}
What it installs
The manifest is a name and a version. 10 skills, 13 commands, 5 agents, 2 hooks travel with it, and installing the plugin installs all of them — 667 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill figma-to-code A 97 tokens
- Skill systematic-debugging A 38 tokens
- Skill finishing-a-development-branch A 43 tokens
- Skill requesting-code-review A 27 tokens
- Skill subagent-driven-development A 0 tokens
- Skill test-driven-development A 0 tokens
- Skill writing-plans A 0 tokens
- Skill brainstorming A 78 tokens
- Skill executing-plans A 53 tokens
- Skill planning-with-files A 108 tokens
- Command pdforge A 0 tokens
- Command accept A 0 tokens
- Command tdd A 0 tokens
- Command build-fix A 0 tokens
- Command learn A 0 tokens
- Command review A 0 tokens
- Command design A 24 tokens
- Command plan A 0 tokens
- Command update-docs A 0 tokens
- Command brainstorming A 22 tokens
- Command deploy A 0 tokens
- Command prd A 25 tokens
- Command fix A 18 tokens
- Agent prd-generator A 44 tokens
- Agent tdd-guide A 32 tokens
- Agent architect A 33 tokens
- Agent implementer A 25 tokens
- Agent planner A 0 tokens
- Hook PostToolUse A not measured
- Hook PreToolUse 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.
- 1mo ago First seen · 23 lines scan A dd0a98136b86
pdforge is a plugin published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d 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
knowledge-virtuoso
17 knowledge skills: design patterns, refactoring, SOLID, debugging, clean architecture, testing, API design, security, agent security, context engineering, docs lookup, scrum, performance, microservices, CI/CD, accessibility, and database design.
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.
whetstone
Engineering-craft skills: red-green TDD, flaky-test audit, diagnosis, doubt review, grilling, merge-conflict resolution, research reports with grounded claims, HTML reports, skill linting and a column budget. Every gate among them carries a deterministic self-verify.
es6kr
Core fundamental skills: brief, fa, tdd, and web-browser.
superpowers-deepseek-v4
Superpowers DeepSeek v4: composable agent skills for TDD, debugging, and collaboration. Independently maintained; not identical to obra/superpowers.
safeword
AI coding agent workflows: BDD, auto-linting, quality reviews, debugging, and refactoring. Run safeword install in a project to enroll it.