Plugin Claude Code
Bundles 29 skills, 1 MCP server · 2,665 tokens together
Autonomous AI research harness for Claude Code. Plan -> Research -> Build -> Audit -> Run -> Assess -> Codify, with adversarial subagent review, a taste corpus, a [LEARN] memory system over SQLite/FTS5, and a spot-first GPU procurement router.
Skill Claude CodeCodex
Build any goal-declared agent end to end. Turns one declared goal into a portable, self-hardening, publishable agent repo on the Claude-Code harness. Declare goal, pick runtime/tools and write policies/hooks/safeguards, scaffold a portable repo (config-over-code split), build, run a fresh no-memory adversarial…
Skill Claude Code
This agent's own internal adversarial critic loop. Hardens every deliverable with a fresh no-memory domain critic until it passes twice consecutively with zero CRITICALs before return.
MCP server Claude CodeCodexCursor +2
MCP server "github-mcp" as configured in Rockielab/rockie-codex. Launched with REPLACE_WITH_LAUNCH_COMMAND.
Skill Claude CodeCodex needs its repo
Continuous-operation mode for rockie — runs the experiment queue autonomously, using Zero-Cost Monitoring ($0 LLM cost during training), anti-burn exponential cooldown on failures, and ntfy to wake the human only when a decision is needed. Use when you want agent-driven research to proceed for days without human…
Skill Claude CodeCodex
Canonical around-the-clock research loop. Defines the agent's outer loop — read taste corpus + queue, pick the next experiment, mutate the explicitly-declared mutation surface, run the experiment under a hard time budget against a frozen metric, score, codify, repeat. Augmented with Karpathy's sharp primitives (frozen…
Skill Claude CodeCodex
Build a pre-deploy Rockie GPU budget term sheet before any Rocky-originated experiment submit. Trigger words "/budget-term-sheet", "quote the GPU budget", "show me the term sheet", or any workflow that is about to call /experiment for GPU / torch / triton / training / weight-download work.
Skill Claude CodeCodex
Lab composer command scaffold for /build-agent . In Agent Builder A1 this only creates a lab-scoped draft agent record and opens that lab's agent detail route for editing. It does not build, run, evaluate, observe, or deploy agents yet.
Skill Claude CodeCodex
Pre-commit anti-slop audit — checks staged/dirty files for code slop (debug artifacts, single-use helpers, dead imports) AND documentation slop (stale claims, broken internal links, new .md files, redundant sections). Writes a sentinel so the pre-commit-gate hook lets the commit through. MUST be invoked before git…
Skill Claude CodeCodex
Narrow quickstart wrapper for pre-baked Deploy-card requests. Triggers on server-validated structured quickstart deploy prompts such as "Quickstart deploy request: track: deploy model: source: quickstart-picker quickstartintentid: " and explicit "deploy this featured model" requests from Rockie's quickstart picker…
Skill Claude CodeCodex
Dispatch a small team of Codex agents to think through a problem in parallel and return a combined report. Use for research gauntlets (brainstorm / research / attack / validate), pre-launch code audits (security / correctness / simplicity), post-run analysis (positive / adversarial / contextualizer), or blog-coherence…
Skill Claude CodeCodex
Produce structured acquisition due-diligence findings from deal inputs and a private data room. Triggers on "run diligence", "due diligence on", "diligence deck", "DD findings", "acquisition analysis", "data room", "ingest data room", "/diligence".
Skill Claude CodeCodex
Create validated Excel .xlsx workbook artifacts with XlsxWriter, formula-injection protection, and Rockie artifact emission.
Skill Claude CodeCodex
Run a materials-science / ML compute job on Rockie GPU capacity. Trigger words "run experiment", "submit job", "use the experiment skill". Picks the right GPU type and count from a natural-language description (DFT for QE/VASP/ABINIT, MD for GROMACS/LAMMPS/OpenMM, training for PyTorch/JAX), generates the script…
Skill Claude CodeCodex
Pull expert skills into this harness from the Rockie platform catalog (300 skills across ML training/inference, biology, chemistry, physics, databases, coding). Use BEFORE writing domain guidance from scratch or fumbling an unfamiliar framework — if the task names a library (vLLM, GRPO, TRL, AlphaFold, DuckDB…
Skill Claude CodeCodex needs its repo
Track 2 quickstart wrapper for structured fine-tune prompts using a registry model, a registry dataset, Rockie GPU jobs, and inference-loader deployment of the trained artifact.
Skill Claude CodeCodex
One-time onboarding flow for users who set ROCKIEGPUMODE=custom (i.e., they have their own GPU setup — own AWS account, on-prem cluster, SSH tunnel to a workstation, university HPC, custom orchestration — instead of using Rockie's deidentified GPU router). Trigger this when (1) the user mentions…
Skill Claude Code
When the user (or you) needs to know GPU spend — "what's my burn rate?", "how much have I spent this week?", "is anything still running?", "am I close to budget?", "what's running idle?" — invoke this. Wraps rockie-gpu spent --json (the deidentified Rockie-GPU spend surface) for accurate, reconciled numbers, then…
Skill Claude CodeCodex
Productize an open-source model into a hosted inference endpoint the researcher (or their agent) can call. Picks the right hardware, the right serving stack (vLLM / Triton / TEI / BentoML), wraps it in an OpenAI-compatible gateway (LiteLLM) with per-tenant auth, exposes it as an MCP tool in chat, and runs a quality +…
Skill Claude Code
Manage swappable operational overlays on top of the central taste corpus. A mode is a small TOML file capturing how this session's policy differs from the researcher's stable identity — hardware preferences, budget ceilings, reading focus, scope-lock, subagent model policy, output register, deadlines. The active mode…
Skill Claude Code
One-time researcher onboarding interview that compiles a taste/ corpus (SOUL.md, STYLE.md, METHODOLOGY.md, DISMISSALS.md, MEMORY.md, INDEX.md) capturing the researcher's intellectual taste, beliefs, and values. Auto-injects INDEX.md into every future session via SessionStart. Triggers on first install ("no taste…
Skill Claude CodeCodex
Write submission-grade research papers end to end inside a Rockie lab, the way a careful human researcher does — not generic LLM filler. Three entry points. /lit-review pulls and ranks a corpus and persists a human reading list Note plus a machine-readable index Note. /paper-draft produces a brief, a page-budgeted…
Skill Claude CodeCodex
Route physics simulation, modeling, validation, and research-compute requests across force fields, molecular dynamics, electronic structure, particle transport/collision, continuum multiphysics, plasma/PIC, nuclear/radiation, and astro/cosmology. Use open-source-first engines, refuse local heavyweight execution on the…
Skill Claude CodeCodex
After an experiment finishes, structured review emits {isbug, failureclass, summary, metric, lowerisbetter}, auto-closes the journal node, emits a [LEARN] block when isbug=true, and files a [DEAD-END] when the failureclass is "bad-hypothesis". Use immediately after any training/eval run — the agent invokes this…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: