act101
claudecodexAST-aware code transformer for AI agents. 140+ refactoring operations across 100+ languages with undo/redo, preview mode, and intelligent guardrails.
26 skills · 3 commands · 3 agents · 1 MCP server
AST-aware code queries, code-health and dependency analysis for AI agents across 43 languages: skeletons, symbols, repository outlines, definitions, references and callers; structural patterns, hotspots and duplicated code; and file dependency graphs, cycles, coupling and impact, over MCP.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin act-lite in act101-ai/act101. Commands read from the repo's manifest — yesterday.
This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.
audit-debtAudits technical debt in a repository or directory: where complexity concentrates, which functions exceed structural thresholds, and where code is duplicated. Use when the operator asks for a tech-debt audit, a code-health audit or where to start cleaning up.
define-workTurns a request into an approved design document before any code is written. Use when the operator asks to build, add, change or design something whose intent, scope or constraints are not yet settled ("I want to add…", "what should we build", "help me think this through", "let's design this"), or a
deliver-workTakes finished work to a reviewed, CI-green pull request, reports it, and carries out a merge or discard only when the operator authorizes it. Use when implementation is complete and the operator asks to finish, wrap up, ship, deliver or open a PR for the work ("open a PR", "ship it", "we're done, w
diagnose-defectFinds the root cause of a defect and fixes it at the cause, proven by a test that failed first. Use when something is broken and its cause is not yet known, before proposing a fix: a bug, a failing or flaky test, a crash or error message, a regression ("this used to work"), a failure seen only in CI
execute-workRuns a work graph to completion, schedules the ready nodes in parallel, plans and implements each node test-first in its own checkout through its fixed acceptance check and a verification stage, keeps or discards, archives, and hands the finished branch to delivery. Use when the operator asks to run
map-repoMaps a repository for orientation: its languages and size, where complexity concentrates, and how the most complex files connect to the rest. Use when the operator or an agent is new to a repository, asks for an overview, a map, a tour, or where to start reading.
plan-workPlans work as a resumable work graph of nodes with contracts, dependencies and fixed acceptance checks, cut from an approved design, reviewed, validated and committed for execution. Use when the operator asks to write a plan, plan a change, break work down or turn a spec into tasks before writing co
review-changeReviews a change for code health: structural problems in the changed functions and duplication that touches the change. Use when the operator asks to review a diff, branch, commit range or pull request for complexity, size, nesting, parameter lists or duplicated code.
work-graphThe work graph format that plan-work creates and execute-work runs. Load it when you have to read, validate, hand-edit or archive a work graph (graph.md, nodes/<id>.md, history.md, backlog.md), map a graph to another ledger, or run scripts/work_graph.py (check, ready, status, archive).
act-literuns: act-lite mcp serve
AST-aware code transformer for AI agents. 140+ refactoring operations across 100+ languages with undo/redo, preview mode, and intelligent guardrails.
26 skills · 3 commands · 3 agents · 1 MCP server
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 1 MCP server
Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.
12 skills · 1 MCP server · hooks
daisyUI Blueprint MCP server - (Needs paid license)
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.