claude

Murmuration

A research team for Claude Code: a principal investigator who follows what does not add up, and colleagues who explore, author claims and verify them independently. Claude Code only; macOS and Linux.

0 on GitHubby Eliott Jacopinv0.3.1AGPL-3.0-onlyupdated 3 days agoProductivity
/

Plugin murmuration from marketplace cracking-shells in CrackingShells/Nest. Commands read from the repo's manifest — 3 days ago.

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 (3)

  • lab-status

    Show the state of the Murmuration research lab in the current project: open puzzles, the current state of every claim, and spend in USD. Run it as `/lab-status`.

  • lab

    Start a Murmuration research lab in the current project, or add a new question to the lab that is already there. Run it as `/lab <your question>`.

  • research-loop

    Working procedures of a Murmuration research team — roles and agent types, how to name agents and identifiers, the formats of claims, verdicts, puzzles and wave notes, the claim labels and what each verdict does to them, and the order in which an author and a verifier work. Load at the start of ever

Subagents (5)

  • author

    Murmuration author. Turns a hunch into a labelled claim by proof or by experiment, files it under __pondus__, and answers its paired verifier directly.

  • explorer

    Murmuration explorer. Probes an open direction or surveys prior work under a loose brief and returns raw material, the case that fits worst, and the puzzles it finds.

  • proof-adversary

    Murmuration verifier for proofs and exact claims. Assumes the claim is wrong until each step is checked, records its own result first, then questions the author directly, and closes the claim with a verdict.

  • reproducer

    Murmuration verifier for empirical claims. Records its own independent result first, then questions the author directly, and closes the claim with a verdict.

  • research-pi

    Principal investigator of a Murmuration research team. Runs as the main-thread agent of a lab project; leads explorers, authors and verifiers on a question the user cares about.

Hooks (11)

  • UserPromptSubmit

    python3

  • SessionStart

    python3

  • SessionStart

    python3

  • SubagentStart

    ${CLAUDE_PLUGIN_DATA}/bin/murmuration.exe

  • PreToolUse

    ${CLAUDE_PLUGIN_DATA}/bin/murmuration.exe

  • PreToolUse

    ${CLAUDE_PLUGIN_DATA}/bin/murmuration.exe

  • PostToolUse

    ${CLAUDE_PLUGIN_DATA}/bin/murmuration.exe

  • PostToolUse

    ${CLAUDE_PLUGIN_DATA}/bin/murmuration.exe

  • SubagentStop

    ${CLAUDE_PLUGIN_DATA}/bin/murmuration.exe

  • SubagentStop

    ${CLAUDE_PLUGIN_DATA}/bin/murmuration.exe

  • PostToolBatch

    ${CLAUDE_PLUGIN_DATA}/bin/murmuration.exe

View source on GitHub

More from CrackingShells/Nest

All 15 plugins →

colgrep

claudecodex

Semantic and hybrid code search for coding agents, exposed as MCP tools backed by colgrep.

5 skills · hooks

0

Maintainer skills for this repository (policy, campaign leadership, landing and release, stack traps). Not for end users.

4 skills

0

Coins a precise new word and its morphological family for a concept that lacks a compact name.

1 skill

0

Designing Tests

claudecodex

Designs software tests and statistical tests before they are written, so each answers a stated question and can fail.

1 skill

0

Turns a Claude Design figure or table into a print-quality image placed, undistorted, into a local document.

1 skill

0

Creates, executes, and amends graph-based campaign roadmaps.

1 skill

0

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

Maintain Murmuration?

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 plugins15 plugins