15,663 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Vibgrate AI Context for Claude Code: a local-first MCP server with a deterministic code map (impact, navigation, search) plus version-correct, drift-annotated library docs. No API key.
★not rated 3 todayA
tokens not measured
originalApache-2.0
Index any TypeScript/React repo (incl. monorepos) into a queryable code graph — npx CLI, HTTP/WS server, and MCP server. Reverse queries (who-renders/who-calls/find-references), blast-radius, cycles, dead-code orphans, symbol signatures, external (nodemo. Runs locally from the code-graph-indexer npm package.
Set up, configure, and use Mushi Mushi — the AI-powered QA platform for automatic bug detection, user story mapping, TDD scenario generation, and PDCA auto-improvement. Use when setting up Mushi, configuring SDK/CLI/MCP, managing API keys, or asking how any Mushi feature works.
Find the LLM call you didn't need — your GPT call is a regex. Static, zero-config linter that flags unnecessary GPT/Claude/AI API calls a regex, the stdlib, or a library already does (parsing dates, extracting emails/JSON, sorting, classifying with fixed labels). Runs locally, no model, no API key, nothing phones…
Skills that teach any agent to answer code questions structurally instead of reading whole files — symbol lookup, callers, imports and blast radius. Bundles the codeindex MCP server so install wires everything in one step.
★not rated 3
changed 4d agoA
tokens not measured
originalMIT
Orchestrate a full-project consistency audit using a parallel agent team. Spawns lane-specific auditors to cross-reference docs vs code vs tests vs infra, deduplicates findings, and writes a severity-scored audit report.
Use this skill when the user asks to audit a codebase for LLM API calls (OpenAI, Anthropic — Python and TS/JS SDKs plus equivalent raw HTTP) and decide which calls can be replaced with deterministic logic. Activates on phrases like 'audit LLM usage', 'bust LLM calls', 'bust the LLM here', 'llm-bust this', 'do I…
A Chinese-language, end-to-end coding workflow with separate steps for planning, review, approval, implementation, checking, and final audit. It also includes optional requirement drafting and log-based cause analysis.
Check whether a repository agrees with itself, for Claude Code and Codex - broken links, dangling heading anchors, orphaned files, duplicate and near-duplicate content, and translations that have fallen behind. Deterministic: no model calls, no network, no dependencies, and it never modifies the repository it scans.…
★not rated 3 26d agoA
tokens not measured
originalMIT
Failure-mode-driven reliability engineering — enumerate how it breaks, give every mode a verdict, prove every handler with a reproducing test. Use when the user says "flaky", "harden this before launch", "what if this fails", "error handling", "timeout", "retry", "idempotency", or "race condition"; when an incident or…
Kit-maintainer diagnostic (LOCAL-ONLY, not distributed) that audits the README and docs/ for staleness against the repo's real command/skill/CLI roster, stamped tree, and cross-doc consistency. Read-only; produces a severity-ranked findings report.
Plans before it edits, routes each step to haiku, sonnet or opus by cost, and verifies four ways per wave. Ships tiered subagents, authoring skills, local MCP tools, and gated fail-open hooks.
★not rated 3
changed 7d agoA
tokens not measured
originalMIT
★not rated 3 8mo agoA
tokens not measured
originalMIT
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: