md-scanner

Obsidian vault integration for Claude Code. Auto-capture git commits, save sessions, query past work with /recall, export conversations. Supports user-defined VAULT.md conventions.

11 skills · 8 commands · 2 agents · hooks

Autonomous CEO agent. Reads Obsidian vault, dispatches 6 specialized subagents, 8 playbooks, 7 skills, cron execution pipeline with three-phase tier enforcement. CLI with setup/doctor/test.

8 skills

Dispatch long-running research tasks to the Manus AI agent platform from Claude Code via slash command. SessionStart + Stop hooks surface newly-completed tasks both on next session and mid-conversation (zero extra Claude turns). Retrieves file deliverables from their signed CDN links, so a task whose payload is an attachment no longer looks complete with the payload missing. On-demand polling, optional Obsidian filing, explicit-invocation cost gating.

3 commands · hooks

Source-grounded project glossary. Auto-invokes when the agent encounters an unfamiliar acronym or project-specific term in a registered repo: resolves the current cwd to a domain via per-machine config (with git-worktree fallback), reads the matching glossary, and answers cited rather than guessing. Also handles seed (build candidates from commits / GitNexus / docs) and drift-check (verify every citation still resolves).

1 skill · 1 command

Auto-compact when context fill crosses thresholds. Stop-hook gate computes fill % from the live transcript; fires an advisory at 35% and escalated nudge at 50%, both directing /compact. Context-window divisor is a dynamic var (CONTEXT_LOOP_WINDOW override; falls back to Opus 1M / other 200K heuristic).

1 skill

Token spend analytics and cost alerts for Claude Code. 16 report modes including weekly credit consumption against your plan cap, cache intelligence, tooling analysis by layer, per-artifact Write/Edit cost analytics, and a credit-denominated auto-checkpoint hook.

1 skill

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

Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.

2 commands

Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement

3 skills · 6 commands · 1 agent

Long-term semantic memory for Claude Code, powered by OpenViking

5 skills · 1 command · 1 MCP server · hooks

Search and retrieve documents from local markdown files.

2 skills

Persistent memory for AI coding agents -- captures tool usage, compresses via LLM, injects context into future sessions

17 skills · 1 MCP server · hooks