Agent Claude Code
Investigates one subtopic by crawling URLs and extracting usage-focused code examples.
not rated 1 3mo ago A 14 tokens
original MIT
Agent Claude Code
Formats validated, synthesized research into TUI-ready artifacts and reports progress.
not rated 1 3mo ago A 13 tokens
original MIT
Agent Claude Code
Converts vague topics into structured research plans with subtopics, questions, and seed URLs.
not rated 1 3mo ago A 17 tokens
original MIT
Agent Claude Code
Merges validated research into a structured, practical final report with code examples.
not rated 1 3mo ago A 14 tokens
original MIT
Agent Claude Code
Cross-checks research outputs for contradictions, hallucinated claims, and missing sources.
not rated 1 3mo ago A 15 tokens
original MIT
forge-commit
06Command Claude Code
Generate a Conventional Commits message from staged git changes.
not rated 1 3mo ago A 10 tokens
original MIT
forge-docs
07Command Claude Code
Generate or review documentation for the specified file or module.
not rated 1 3mo ago A 10 tokens
original MIT
Command Claude Code
Execute the deep research pipeline via the deep-research skill: topic → structured report.
not rated 1 3mo ago A 16 tokens
original MIT
forge-review
09Command Claude Code
Review staged or specified files for code quality, security, and performance issues.
not rated 1 3mo ago A 14 tokens
original MIT
forge-search
10Command Claude Code
Quick single-search via websearch tool: lightweight web lookup for when context is missing.
not rated 1 3mo ago A 16 tokens
original MIT
forge-start
11Command Claude Code
Context launcher — load AGENTS.md for full framework rules, then use this as a quick-reference guide.
not rated 1 3mo ago A 20 tokens
original MIT
forge-test
12Command Claude Code
Generate comprehensive tests for the specified file or module.
not rated 1 3mo ago A 9 tokens
original MIT
settings
13Settings file Claude Code
Agent settings declaring 13 hook events (UserPromptSubmit, PreToolUse, PostToolUse, PostToolUseFailure).
not rated 1 3mo ago A
tokens not measured
original MIT
Skill Claude Code
Creates and configures subagents dynamically with defined roles, constraints, and tool permissions.
not rated 1 3mo ago A 20 tokens
original MIT
Skill Claude Code
Designs system-level structures including modules, services, data flow, and scaling strategy before implementation begins.
not rated 1 3mo ago A 22 tokens
original MIT
Code Builder
16Skill Claude Code
Translates plans into working code structures with architecture decisions, folder layout, and implementation strategy.
not rated 1 3mo ago A 20 tokens
original MIT
Skill Claude Code
Status: DEPRECATED.
not rated 1 3mo ago A 0 tokens
original MIT
Skill Claude Code
Reads AGENTS.md + project structure + existing skills to build an execution-aware context before any operation.
not rated 1 3mo ago A 22 tokens
original MIT
Skill Claude Code
Guide a new contributor through the ForgeWeave repo — project structure, development setup, branch strategy, and how to pick and start an issue.
not rated 1 3mo ago A 33 tokens
original MIT
Debugger
20Skill Claude Code
Systematic issue diagnosis skill that isolates root causes, tests hypotheses, and produces minimal fix strategies.
not rated 1 3mo ago A 20 tokens
original MIT
Skill Claude Code
Multi-stage research pipeline that decomposes a topic, gathers structured information, validates it, and synthesizes a final report. Supports formatted/unformatted output and skill/no-skill generation modes.
not rated 1 3mo ago A 40 tokens
original MIT
Skill Claude Code
Handles local persistence of research outputs, intermediate reasoning, and reusable knowledge chunks.
not rated 1 3mo ago A 17 tokens
original MIT
Planner
23Skill Claude Code
Converts user intent into structured execution plans, including steps, dependencies, risks, and required tools.
not rated 1 3mo ago A 21 tokens
original MIT
Skill Claude Code
Complete guide for using Playwright MCP to automate browsers inside AI agent workflows. Use this skill whenever the agent needs to: navigate web pages, fill forms, click elements, take screenshots, mock API responses, manage cookies/localStorage, save auth state, generate Playwright test code, record video/traces…
not rated 1 3mo ago A 156 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: