checkpoint

Pipeline orchestration — queue plans, autonomous dev/test/review sessions, merge runner, TUI + web dashboards, spend governance

4 skills · hooks

Two-way Slack ↔ Claude Code bridge via Socket Mode

2 skills · 1 MCP server · hooks

Alternative-model fan-out engine — manifest-driven parallel runs across capable :cloud models and Claude, with digest compression and worktree isolation

3 skills · hooks

Investigate agent transcripts and subagent investigation tooling

1 skill · 1 command

Peer discovery and real-time messaging between local Claude Code sessions — stdio MCP server + self-healing localhost broker

1 MCP server

Per-model discipline deltas injected on every prompt (Sonnet 5 first), with baseline scanner and blind judge grader for measuring violation rates

hooks

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

Cache-aware /loop workers and CronCreate background automation

2 skills · 2 commands · 1 agent

Generate an explorable HTML report of Claude Code session usage — tokens, cache efficiency, subagents, skills, and the most expensive prompts — from local ~/.claude/projects transcripts.

1 skill

Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.

10 skills · 2 commands · 3 agents

Engineer an agent's forgetting, not just its remembering. Four deterministic stdlib scripts implement the four lenses of agent memory: a cost profiler that splits construction from query spend and reports cost per correct answer (construction energy exceeds total query energy across 300 queries in the Stanford characterization); an architecture picker that scores the four paradigm families — long-context, flat RAG, structure-augmented RAG, agentic — disqualifies on hard constraints, names the cost the winning choice makes you pay, and refuses to pick when the top two tie; a density auditor that classifies every record in a memory directory or JSONL export as FACT / SKILL / LOG / PROSE, finds near-duplicates, and flags stale wording; and a forgetting-policy linter that fails any design with no forgetting rule. Ships cs-memory-engineer agent, /cs-memory-engineering and /cs-forgetting-audit commands, 4 references, and a seven-question forcing worksheet.

1 skill · 2 commands · 1 agent

Comprehensive context engineering and harness engineering skills for production-grade AI agent systems: fundamentals, degradation patterns, compression, optimization, self-managed context (model-controlled live context editing), multi-agent coordination, long-horizon prompting (pseudo-formal task briefs for long-running and parallel agents), memory systems, tool design, filesystem context, hosted agents, evaluation, autonomous harnesses, self-improvement loops (RSI, meta-harnesses, evolutionary scaffold search), latent briefing (KV cache sharing between agents), project development, and cognitive architecture. Ships with a researcher operating system (rubrics, mechanism registry, claim provenance, run state machine, adversarial benchmarks, continuous loop).

19 skills