Access GitHub repository documentation and AI-powered Q&A via DeepWiki - compare repos, explore architecture, quickstart guides, deep dives, and troubleshooting.
★not rated 9 5mo agoA
tokens not measured
originalMIT
AI Development Methodology: 6 phase gates from discovery to ship, 28 skills, 38 review sub-agents, and WHY-first enforcement hooks. Stops code being written before the problem is understood.
Project configuration and setup tools including CLAUDE.md creation and maintenance with ground truth validation. The maintain flow preserves existing references and information by default - removal requires cross-verification proving the content false or obsolete (else: keep, extract to docs/, or ask the user) - and…
★not rated 9 yesterdayA
tokens not measured
originalMIT
You say the job; the playbook runs. 145 agent skills, 57 slash commands, 6 subagents, and MCP templates for React / Next.js / Supabase — also works in Claude Code.
★not rated 9
changed 3d agoA
tokens not measured
originalMIT
Catches agent configuration that grants more than it appears to: permission rules whose wildcards reach further than they read, broken skill references, and MCP servers that will silently fail to load.
★not rated 9 6d agoA
tokens not measured
originalMIT
Apple Mail MCP server plugin — archive-mail SOP commands, compose and confirmation rules, and the wrapper that downloads the signed, notarized binary pinned by binaryversion. Release narrative and version history live in CHANGELOG.md.
★not rated 8
changed 7d agoA
tokens not measured
originalMIT
Hostile, bias-free review of a change — dispatches independent adversarial reviewers that hold the code against what was agreed and question whether what was agreed was right, plus a standalone false-positive filter, and reports only verified findings in plain language. Ships a full 18-reviewer panel and a cheaper…
★not rated 8
changed todayA
tokens not measured
originalMIT
Grapevine 🍇 — shared awareness for independent Claude Code sessions: observes what each session touches, maps the dependencies between them, and nudges a session when its edit affects a peer.
★not rated 8 1mo agoA
tokens not measured
originalMIT
A session-based working method for coding agents: plan an epic into thin complete slices, build one at a time, verify by observing real behaviour, and hand off so the next session starts where the last one stopped.
★not rated 8 1mo agoA
tokens not measured
originalMIT
A runtime that injects declared module boundaries into an agent's context when the agent edits nearby files. A module boundary describes which parts of a codebase belong together and may interact.
★not rated 8
changed 8d agoA
tokens not measured
originalApache-2.0
Audience-building workflows backed by the narrative-mcp server — turning marketing briefs into filtered, materialized audience datasets and activating them to downstream advertising connectors.
★not rated 8 todayA
tokens not measured
originalMIT
Autonomously research any technology and generate reusable Claude Code skills.
★not rated 8 7mo agoA
tokens not measured
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: