Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By mistakeknot
Work prioritization and next-task analysis for Claude Code — tradeoff-aware recommendations from project state.
npx claudepluginhub mistakeknot/interagency-marketplace --plugin internextWork prioritization for Claude Code.
internext reads your project's beads state and recommends what to work on next. Not a neutral menu of options: an opinionated recommendation with explicit tradeoff analysis.
Each candidate gets scored on three axes: impact (does it unblock other work? does it build capability?), effort (30 minutes or multi-session?), and risk (mechanical task or rabbit hole?). Items that block other items get an impact bonus: a P2 that unblocks three P1s is worth more than a standalone P1.
There's a built-in completion bias: finishing in-progress work almost always beats starting new work, because the switching cost of abandoned context is real and consistently underestimated.
First, add the interagency marketplace (one-time setup):
/plugin marketplace add mistakeknot/interagency-marketplace
Then install the plugin:
/plugin install internext
/internext:next-work
Or ask naturally:
"what should I work on next?"
"prioritize my backlog for this session"
The skill reads from bd ready, bd list, and bd stats to build its picture of the project state, then delivers 3-5 scored options with a clear recommendation.
AI-supervised issue tracker for coding workflows. Manage tasks, discover work, and maintain context with simple CLI commands.
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Convert design documents, PRDs, and task lists into beads issues with lossless conversion, proper epic hierarchy, validated dependencies, and three independent subagent review passes.
Configure Claude Code to track work using Beans.
Sprint planning with story prioritization and capacity estimation
Personal task tracker — invisible kanban that tracks your work automatically
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
[DEPRECATED — use intervoice] Analyze your writing style and adapt Claude's output to sound like you. Replaced by intervoice, which reads one global multi-register profile instead of per-project glob-routed files.
Recursive AGENTS.md generator with integrated Oracle critique, CLAUDE.md harmonization, incremental updates, diff previews, and smart monorepo scoping. Cross-AI compatible.
Self-improving agent rig: codifies product and engineering discipline into composable workflows from brainstorm to ship. Compounds knowledge, generates domain agents, monitors its own docs, and surfaces conservative update drift. Orchestrates Claude, Codex, and Oracle through 6 agents, 52 commands, 19 skills, 0 MCP servers. Factory substrate: CXDB turn DAG, scenario bank with satisfaction scoring, evidence pipeline, agent capability policies. Companions: interspect, interphase, interline, interflux, interpath, interwatch, interslack, interform, intercraft, interdev, interpeer, intertest.
Token-efficient code reconnaissance for LLMs. Autonomous skills save 48-85% tokens via diff-context, semantic search, structural patterns, and symbol analysis. Includes MCP server for direct tool integration.
Token efficiency benchmarking, session analytics, and API-equivalent cost analysis for agent workflows
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim