claude

research

Reviewable ML research: literature, planning, methodology review, bounded runs, sweeps, implementation verification, ablations, retrospectives, Kaggle, and setup

31 on GitHubby Jirkav0.33.4Apache-2.0updated today
/

Plugin research from marketplace borda-ai-rig in Borda/AI-Rig. Commands read from the repo's manifest — today.

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.

What it installs

Skills (10)

  • fortify

    Systematic ablation study runner. After research:run finds improvements, fortify identifies component candidates from git diff + diary, creates isolated git worktrees per ablation (main repo never modified), runs metric+guard in each worktree, ranks component importance, and optionally generates rev

  • judge

    Research-supervisor review of program.md — validates experimental methodology (hypothesis clarity, measurement validity, control adequacy, scope, strategy fit), emits APPROVED / NEEDS-REVISION / BLOCKED verdict before expensive run loop.

  • kaggle

    Generate a Kaggle competition notebook as a Jupytext `# %%` Python script following the user's established ML research style: PTL for DNN training, best-fit tool selection, EDA→Baseline→Train→Inference pipeline with per-stage lens cells, small single-purpose cells each carrying a why. Grounds data s

  • plan

    Interactive wizard that scans the codebase, proposes a metric/guard/agent config, and writes a program.md run spec. With confirmation, runs cProfile on a Python file path to surface bottlenecks before prompting for optimization goal. Distinct from `/research:topic plan`, which turns prior SOTA resea

  • retro

    Post-run retrospective: reads .experiments/ JSONL, computes Wilcoxon significance, detects dead iterations, flags suspicious jumps, generates next-hypothesis queue for --hypothesis flag.

  • run

    Sustained metric-improvement loop with atomic commits, auto-rollback, and experiment logging. Iterates with specialist agents, commits atomically, auto-rolls back on regression. Accepts a program.md file path. Supports --resume, --team, --colab, --codex, --researcher, --architect, --journal, --hypot

  • setup

    Post-install setup for the research plugin. Run once after installing on a new machine, or after a plugin version upgrade, to deliver this plugin's rules/*.md into ~/.claude/rules/ as namespaced symlinks and merge its own permissions.allow and permissions.deny entries into ~/.claude/settings.json. T

  • sweep

    End-to-end pipeline with J4 per-command execution approval — auto-configure program.md (accept defaults), run judge+refine loop (up to 3 iterations), then run the campaign. Single command from goal to result.

  • topic

    Research State of the Art (SOTA) literature for an Artificial Intelligence / Machine Learning (AI/ML) topic, method, or architecture. Finds relevant papers, builds a comparison table, recommends the best implementation strategy for the current codebase, and optionally produces a phased implementatio

  • verify

    Paper-vs-code consistency audit. After research:scientist implements a method from a paper, verify the implementation matches paper claims across five dimensions — formula matching [F], hyperparameter parity [H], eval protocol [E], notation consistency [N], and citation chain [C]. Reads paper (PDF p

Subagents (2)

  • data-steward

    Data lifecycle specialist — dataset acquisition, DVC versioning, split audits, leakage detection, DataLoader config. Manual invocation only — no research skill auto-dispatches this agent. Delegates scraping to foundry:web-explorer. NOT for ML experiment design (research:scientist), DataLoader throug

  • scientist

    AI/ML researcher — paper analysis, hypothesis generation, experiment design. ONLY for named research paper/hypothesis/experiment. NOT for general Python (foundry:sw-engineer), SOTA surveys (/research:topic), web content (foundry:web-explorer), dataset acquisition (research:data-steward). TRIGGER: im

Hooks (14)

  • PostToolUse

    for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v "$n" >/dev/null 2>&1 && exec "$n" "${CLAUDE_PLUGIN_ROOT}/hooks/audit-close.js"; done; exit 0

  • PostToolUse

    for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v "$n" >/dev/null 2>&1 && exec "$n" "${CLAUDE_PLUGIN_ROOT}/hooks/enforce-topic-header.js"; done; exit 0

  • PostToolUseFailure

    for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v "$n" >/dev/null 2>&1 && exec "$n" "${CLAUDE_PLUGIN_ROOT}/hooks/audit-close.js"; done; exit 0

  • PreToolUse

    for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v "$n" >/dev/null 2>&1 && exec "$n" "${CLAUDE_PLUGIN_ROOT}/hooks/enforce-topic-header.js"; done; exit 0

  • PreToolUse

    for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v "$n" >/dev/null 2>&1 && exec "$n" "${CLAUDE_PLUGIN_ROOT}/hooks/agent-router.js"; done; exit 0

  • PreToolUse

    for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v "$n" >/dev/null 2>&1 && exec "$n" "${CLAUDE_PLUGIN_ROOT}/hooks/allow-dispatch.js"; done; exit 0

  • PreToolUse

    for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v "$n" >/dev/null 2>&1 && exec "$n" "${CLAUDE_PLUGIN_ROOT}/hooks/write-guard.js"; done; exit 0

  • PreToolUse

    for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v "$n" >/dev/null 2>&1 && exec "$n" "${CLAUDE_PLUGIN_ROOT}/hooks/write-guard.js"; done; exit 0

  • PreToolUse

    for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v "$n" >/dev/null 2>&1 && exec "$n" "${CLAUDE_PLUGIN_ROOT}/hooks/write-guard.js"; done; exit 0

  • SessionEnd

    for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v "$n" >/dev/null 2>&1 && exec "$n" "${CLAUDE_PLUGIN_ROOT}/hooks/audit-close.js"; done; exit 0

  • SessionStart

    for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v "$n" >/dev/null 2>&1 && exit 0; done; echo "research plugin hooks are inactive: Node.js not found on PATH, in /opt/homebrew/bin

  • SessionStart

    for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v "$n" >/dev/null 2>&1 && exec "$n" "${CLAUDE_PLUGIN_ROOT}/hooks/audit-close.js"; done; exit 0

  • SessionStart

    for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v "$n" >/dev/null 2>&1 && exec "$n" "${CLAUDE_PLUGIN_ROOT}/hooks/stale-plugin-check.js"; done; exit 0

  • Stop

    for n in node /opt/homebrew/bin/node /usr/local/bin/node; do command -v "$n" >/dev/null 2>&1 && exec "$n" "${CLAUDE_PLUGIN_ROOT}/hooks/enforce-topic-header.js"; done; exit 0

View source on GitHub borda.github.io

More from Borda/AI-Rig

All 7 plugins →

foundry

claude

Claude Code configuration and workflow maintenance: 11 skills, 10 specialist agents, rules, hooks, audit, calibration, and session handover

11 skills · 10 agents · hooks

31

Fifteen evidence-first Codex workflows, one legacy-shim lifecycle manager, fifteen specialist role cards, shared gates, and reviewable artifacts.

16 skills · hooks

31

oss

claude

Open-source maintenance: issue and repository analysis, PR review, feedback resolution, release-readiness assessment, setup, and 4 specialist agents

5 skills · 4 agents · hooks

31

develop

claude

Validate-first Python development: plan, feature, fix, refactor, debug, review, and setup workflows

7 skills · hooks

31

bridge

claudecodex

bridge_CC-Codex: guided setup plus bounded implementation, advice, and review across Claude Code and Codex.

7 skills

31

codemap-py

claudecodex

Static Python structure for Claude Code: indexing, queries, test impact, reference renames, integration, and session telemetry debriefs

6 skills

31

Maintain research?

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.

claude & codex plugins7 plugins