autoresearch plugins

greyhaven-ai/autocontext

Instructions file

Instructions for greyhaven-ai/autocontext, covering claude.md, project overview, repository layout, commands and setup.

greyhaven-ai/autocontext

Skill Claude CodeCodex

Iterative strategy generation and evaluation system. Use when the user wants to evaluate agent output quality, run improvement loops, queue tasks for background evaluation, check run status, inspect runtime artifacts and session branch lineage, or discover available scenarios. Provides LLM-based judging with…

greyhaven-ai/autocontext

Skill Claude CodeCodex

Use when an agent needs to USE knowledge Autocontext already produced - find which scenarios have knowledge, read the playbook and lessons for one, understand the on-disk file and folder layout, and move knowledge between checkouts. Host-agnostic; requires only the autoctx CLI and the filesystem.

greyhaven-ai/autocontext

Skill Claude CodeCodex

Use when an agent needs to CREATE knowledge with Autocontext - run a scenario or plain-language task through the improvement loop, judge or improve a single output, and inspect what the run produced. Host-agnostic; requires only the autoctx CLI.

RUC-NLPIR/Arbor

Plugin Claude Code

Run Arbor's hypothesis-tree research workflow inside Claude Code using your own model — no API key. Bundles the Arbor Agent Skill suite and registers the keyless arbor mcp tools (Idea Tree, evaluation, worktrees, guarded merges, reports).

RUC-NLPIR/Arbor

Skill Claude CodeCodex

Executor-dispatch phase for Arbor. Use when implementing an Idea Tree node through RunExecutor or RunExecutorParallel semantics: isolated git worktree, executor prompt construction, eval metadata injection, RunTraining policy, smoke/full evaluation, report parsing, artifact persistence, tree update, and insight…

RUC-NLPIR/Arbor

Skill Claude CodeCodex

Setup, intake, preflight, and launch-contract phase for open-source Arbor runs. Use when confirming a target project, metric, baseline, dev/test split, config/plugin settings, branch guard, session directory, or when translating a user goal into the precise contract consumed by the coordinator.

RUC-NLPIR/Arbor

Skill Claude CodeCodex

Public entrypoint for the Arbor skill suite. Use when a user wants to run an Arbor-style autonomous research or optimization workflow from a natural-language goal, including initial clarification of objective, target project, data, metric, evaluation, permissions, budget, run mode, and then automatic bootstrapping…

Human-Agent-Society/CORAL

Skill Claude CodeCodex

End-to-end recipe for adding a new task under examples/ — the three pieces that have to line up (task.yaml, seed/, and grader/), what to put in each, the TaskGrader API surface, the coral validate → smoke-test loop, and the common mistakes (repopath pointing at the wrong dir, score direction backwards, hidden answer…

Human-Agent-Society/CORAL

Instructions file CodexOpenCode

Instructions for Human-Agent-Society/CORAL, covering agents.md — ai-assisted contributions to coral, 1. human accountability, 2. scope discipline, 3. duplicate-work checks and 4. keep agent guidance synchronized.

Human-Agent-Society/CORAL

Instructions file

Instructions for Human-Agent-Society/CORAL, covering coral, project overview, directory structure, how it works and tech stack.

Human-Agent-Society/CORAL

Skill Claude CodeCodex

Write a note to {shareddir}/notes/ that future agents can actually act on. Use after every coral eval, when a heartbeat (reflect / consolidate / pivot) asks for a note, or when you discover a grader / build / runtime issue that future agents will hit. Covers 4 note variants (experiment / infra / focus / synthesis)…

Human-Agent-Society/CORAL

Agent

Verify that every claim in a research note is grounded in its linked raw sources.

Human-Agent-Society/CORAL

Agent

Decide what to do with two notes flagged as near-duplicates — without knowing which is which.

Human-Agent-Society/CORAL

Skill Claude CodeCodex

Autonomously create, test, and optimize skills by detecting reusable patterns in your own work. Use when you notice repeated tool sequences, recurring code patterns across attempts, or insights that should be captured as a packaged skill. Also use to benchmark and iterate on existing skills.

Human-Agent-Society/CORAL

Plugin Claude Code

Author and run CORAL tasks from your own harness. Teaches the coral CLI workflow (init/validate, start/status/resume/log/show) and checks coral is installed on session start.

Human-Agent-Society/CORAL

Agent

Use this subagent to turn "optimize / speed up / improve this with CORAL" into a working CORAL task. Give it the code (or just a repo and a rough goal) and it acts immediately — explores the repo to infer the optimization target, scaffolds a .coralworkspace/, writes the grader, and iterates coral validate until the…

Human-Agent-Society/CORAL

Hook

Runs when a session starts on startup, resume, clear and compact, executing session-start.py via python3. From Human-Agent-Society/CORAL.

TheGreenCedar/codex-autoresearch

Instructions file CodexOpenCode

Instructions for TheGreenCedar/codex-autoresearch, covering agents.md, purpose and scope, canonical sources, stable product boundaries and source and package boundaries.

TheGreenCedar/codex-autoresearch

Skill Claude CodeCodex

Triage improvement work and run or resume accepted measured loops in a local project. Architecture, documentation, UX, product study, open research, taste, and one-shot fixes stay direct unless the user explicitly requests repeated measurement with a complete experiment contract.

romovpa/claudini

Skill Claude CodeCodex

Run one iteration of the autoresearch loop — study existing attack methods, design a better optimizer, implement it, benchmark it, and commit. Meant to be called repeatedly via /loop.

romovpa/claudini

Instructions file

Instructions for romovpa/claudini, covering claudini — developer guide, package manager, running benchmarks, run a preset (all methods, all samples) and override method, sample, seed, budget from cli.

gaasher/Agent-Loop-Skills

Plugin Claude Code

Drop-in agentic loop skills — autoresearch, literature & scientific writing, data analysis, code/SQL/prompt optimization, red-teaming, and power analysis. Each loop binds to your own task at invocation time.

gaasher/Agent-Loop-Skills

Skill Claude CodeCodex

Use when the user wants to evolve an ML model/program through population-based search rather than a single sequential refine loop — a generational evolution where parallel proposers each apply one small SEARCH/REPLACE diff to a parent, scored by a cascade-evaluated training run, and children are kept in a MAP-Elites…