claude-mem
claudecodexPersistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Role agents (recon, builder, batch, gate, audit) plus a session policy; pairs with the claude-router proxy, which pins each role's tier and keeps the ledger.
Plugin claude-router from marketplace claude-router in serhiileniv/claude-router. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
auditFresh-context falsification after risky work lands. Tries to refute the claim that the work is complete and correct — runs tests, exercises the change, hunts for the case that breaks it. Reports a calibrated verdict; never edits.
batchApplies the same fully specified edit across many files — renames, signature updates, import rewrites, boilerplate — where each item has its own acceptance check and no design judgement is needed.
builderImplements one scoped, approved change that needs local judgement — a bug fix, a small feature, a refactor with a clear brief. Not for open-ended exploration or for work whose acceptance is still unclear.
gateFresh-context readiness check before risky work is approved — security or trust boundaries, destructive or irreversible changes, schema or migration work, releases, cross-component changes. Reviews a plan or brief; never implements.
reconRead-only reconnaissance. Use for "where is X defined", "what calls Y", "what does this module export", "which files mention Z" — anything answered by reading code, never by changing it.
node "${CLAUDE_PLUGIN_ROOT}/hooks/sessionstart.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/subagent-start.js"
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.
14 skills · 1 command
PowerPoint generation and editing plugin with text-only QA (no vision required). Uses subagents for cover, TOC, content, section dividers, summary slides, and template-based PPT editing workflows.
5 skills · 5 agents
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.
2 skills · hooks
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.