Instructions file
Instructions for theagenticguy/agentic-plugins, covering agentic-plugins, repo structure, harness tool names — do not confuse, no roadmap or migration commentary in skill files and skill architecture: two-tier pattern.
Plugin Claude Code
Flagship skills for AI coding agents. Includes workbench-builder: disposable localhost Bun.serve + bun:sqlite + React 19 + Astryx workbenches with a two-way human↔agent loop over SSE — eval viewers, PR review rooms, document-redline surfaces, grid/spreadsheet editors, multi-surface triage queues, and trace replays…
MCP server Claude CodeCodexCursor +2
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
DeepWiki's hosted MCP server: AI-generated documentation of public GitHub repositories the agent can query. Remote server at mcp.deepwiki.com.
MCP server Claude CodeCodexCursor +2
Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more. Runs locally from the @brave/brave-search-mcp-server npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP server for advanced web search using Tavily. Runs locally from the tavily-mcp npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Connect AI agents to Exa for web search, content fetching, and multi-step research. Runs locally from the exa-mcp-server npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP server "you", hosted remotely at api.you.com, as configured in theagenticguy/agentic-plugins.
MCP server Claude CodeCodexCursor +2
MCP server "awsknowledge", hosted remotely at knowledge-mcp.global.api.aws, as configured in theagenticguy/agentic-plugins.
Skill Claude CodeCodex
Builds disposable localhost workbenches — Bun.serve + bun:sqlite + React 19 + Astryx apps, zero build config, no deploy — giving an agentic coding/eval/PR/data session a live UI. The signature move is a two-way human↔agent loop over one SQLite file: the human acts in the browser, the agent acts from the terminal (bun…
Plugin Claude Code
Catalog hygiene for Claude Code skill/agent plugins. Runs monthly audits: inventory, per-skill scoring, Bedrock Cohere v4 embedding-based collision detection, and HDBSCAN taxonomy checks. Proposes PR-style resolutions without auto-applying.
Skill Claude CodeCodex
Score a single skill against the gardener rubric. Reads the skill's SKILL.md, references/, and templates/, then writes a 7-dimension scorecard with per-criterion rationales and a recommended-actions list. Isolated counterpart to /gardener: same rubric, one item at a time. Use when the user asks to audit a skill, score…
Skill Claude CodeCodex
Monthly catalog hygiene audit for Claude Code plugin marketplaces. Inventories every skill and agent, scores each against a 7-dimension rubric via parallel Opus Agents, detects description collisions via Bedrock Cohere v4 embeddings with pairwise cosine, and writes a delta report vs. the prior audit. Proposes…
Skill Claude CodeCodex
Propose description rewrites to resolve skill collisions. Given a collision pair from a gardener audit, reads both skills' descriptions, generates before/after rewrites with negative discriminators, and writes a proposal Markdown the user applies manually. Uses current Claude prompting discipline: positive…
Agent Claude Code
Use when the user asks to understand code structure, impact of changes, find owners, audit dependencies, or navigate the codebase graph. Specializes in the OpenCodeHub MCP toolkit and always grounds claims in graph queries rather than text search.
Hook Claude Code
Runs before the agent uses a tool for Bash, Grep and Glob tool calls, executing augment.sh via bash. From theagenticguy/opencodehub.
Hook Claude Code
Runs after a tool call finishes for Bash tool calls, executing docs-staleness.sh via bash with --incremental and --quiet (2 commands). From theagenticguy/opencodehub.
Settings file Claude Code
Agent settings declaring 2 hook events (PreToolUse, PostToolUse).
Skill Claude CodeCodex
Use when the user asks for a cross-repo contract map, an API-consumer matrix, or a service-interaction diagram across a repo group. Examples: "map the HTTP contracts between services", "which services call the billing API", "show the contract matrix for the platform group". GROUP MODE ONLY — requires a named group. DO…
Skill Claude CodeCodex
Use when the user asks to generate, regenerate, or refresh long-form codebase documentation, an architecture book, a module map, or a per-repo reference — especially after codehub analyze finishes or after a large merge. Examples: "document this repo", "regenerate the architecture docs", "write a module map for the…
Agent Claude Code
Produce {{ docsroot }}/analysis/dead-code.md: three tables enumerating unreferenced exports, unreferenced files, and dead imports in {{ repo }}. The file is always emitted — when the graph reports no dead code, emit a No unreferenced symbols detected. banner plus a timestamp so Phase E cross-references have a stable…
Agent Claude Code
Produce {{ docsroot }}/analysis/ownership.md: a ranked table of folders in {{ repo }} by top-contributor share, followed by a ## Single points of failure H2 listing paths where the top owner holds > 70% of commits — each SPOF row gets a one-sentence mitigation suggestion.
Agent Claude Code
Produce {{ docsroot }}/analysis/risk-hotspots.md: a ranked table of the top 12 files in {{ repo }} by combined risk score (30-day trend slope + current finding severity), followed by a ## Per-file drill-down section with one H3 per top-5 hotspot covering what's there, recent activity, owners, and open findings.
Agent Claude Code
Produce {{ docsroot }}/architecture/data-flow.md: a walk of the top 3 processes in {{ repo }}, each rendered as numbered steps plus one Mermaid sequenceDiagram. Every step cites path:LOC for the function that advances the flow.