claude

foundry

Name: foundry
Author: J. Greg Williams

Plugin development toolkit: evaluate and improve skills (skillsmith) and agents (agentsmith), and publish them to a marketplace with enforced version bumps (marketplace-manager)

3 on GitHubby J. Greg Williamsv2.2.0MITupdated 2 days agodevelopment

Plugin foundry from marketplace totally-tools in totallyGreg/claude-mp. Commands read from the repo's manifest — 2 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (4)

agentsmith
This skill should be used when users ask to "evaluate my agent", "improve agent quality", "agent metrics", "check agent description", "agent isn't triggering", "validate agent", "agent score", "as-evaluate", "as-improve", "agent quality", "fix agent description", or "why isn't my agent triggering".
marketplace-manager
This skill should be used when managing Claude Code plugin marketplace operations: setup, validation, version-bump enforcement, and plugin scaffolding. Keeps plugin.json the single source of truth and blocks commits that change a plugin or skill without raising its version. Triggers on "setup market
skillsmith
This skill should be used when users ask to "create a skill", "validate a skill for quality", "evaluate skill improvements", "improve my skill", "update my skill", "fix skill", "iterate on skill", "optimize skill", "skill quality", "skill performance", "skill isn't working", "analyze skill metrics",
wtf
This skill should be used PROACTIVELY to "create a friction report", "check for broken tooling", or "run a friction check" when you hit confusing errors, bad docs, missing prereqs, broken tools, misleading skills, flaky tests, auth/MCP failures, or any "this should've been easier" moment. Also trigg

Slash commands (15)

/foundry:as-evaluate
Full evaluation of an agent with quality metrics
/foundry:as-improve
Guided agent improvement loop — evaluate, explain, fix, re-evaluate, update README, check version bumps
/foundry:mp-add
Scaffold a new plugin or migrate a legacy skill into plugin structure
/foundry:mp-list
List marketplace plugins with version, description, and source read from each plugin.json
/foundry:mp-status
Show which plugins and skills changed since main and still need a version bump
/foundry:mp-validate
Validate the marketplace with claude plugin validate plus version-bump, duplicate-metadata, and unregistered-plugin checks
/foundry:ss-evaluate
Full evaluation of a skill with quality metrics
/foundry:ss-improve
Guided skill improvement loop — evaluate, explain, fix, re-evaluate, update README, check version bumps
/foundry:ss-init
Initialize a new skill from template
/foundry:ss-observe
Analyze a Claude Code session transcript to identify skill gaps
/foundry:ss-package
Package a skill directory into a distributable skill.zip
/foundry:ss-refresh
Detect stale references and guide updates for any skill with provenance-tracked references
/foundry:ss-research
Research a skill to identify improvement opportunities
/foundry:ss-validate
Quick structural validation of a skill with optional strict mode
/foundry:ss-wtf
File a friction report or list accumulated friction

Hooks (4)

PostToolUse
bash "${CLAUDE_PLUGIN_ROOT}"/hooks/scripts/on-skill-edit.sh
PostToolUse
bash "${CLAUDE_PLUGIN_ROOT}"/hooks/scripts/on-script-edit.sh
PostToolUse
bash "${CLAUDE_PLUGIN_ROOT}"/hooks/scripts/on-agent-edit.sh
PostToolUse
bash "${CLAUDE_PLUGIN_ROOT}"/hooks/scripts/on-component-edit.sh

View source on GitHub

More from totallyGreg/claude-mp

All 15 plugins →

attache

claude

Chief of Staff agent — personal productivity orchestrator that routes to task backends (OmniFocus, Asana), coordinates cross-tool workflows, and learns patterns across the full tool stack.

4 skills · 13 commands · 1 agent · hooks

archivist

claude

Personal Knowledge Management expert for Obsidian vaults with autonomous orchestration

2 skills · 9 commands · 2 agents · hooks

Multi-skill plugin for Kubernetes Gateway API (kgateway) and AI/LLM routing (agentgateway) — provider backends, MCP server routing, external processing, version lifecycle management, and traffic policies

2 skills · 8 commands · 1 agent

terminal-guru

claude

Terminal diagnostics and tooling for macOS/Unix: terminal emulation, zsh, tmux, TUI apps, signals and logging, mise, and tool composition, with an orchestrator agent and multi-Claude tmux teams.

7 skills · 3 commands · 1 agent

ai-risk-mapper

claude

This skill should be used when identifying, analyzing, and mitigating security risks in Artificial Intelligence systems using the CoSAI (Coalition for Secure AI) Risk Map framework. Use when users ask to "assess AI security risks", "analyze AI system threats", "map risks to controls", "run a risk assessment", "check compliance with MITRE ATLAS", "generate a CoSAI report", or "profile persona risks". Supports LLM applications, ML pipelines, model training/serving infrastructure, and compliance reporting aligned with MITRE ATLAS, NIST AI RMF, OWASP Top 10 for LLM, STRIDE, and ISO 22989 frameworks.

1 skill · 7 commands

condo-steward

claude

Community association steward: parse management-company financial statements into local HTML reports, explain Florida condo/HOA statutes and Division rules, and guide boards and owners — with clear escalation to attorneys, CPAs, reserve specialists, and engineers. Holds no community data; per-community settings live in the project's community.toml.

1 skill · 6 commands

Similar plugins

mattpocock-skills

claude

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

Maintain foundry?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins15 plugins