2389-research

61 mods across 17 repositories, 206 stars between them.

agent-drugs

25

2389-research/agent-drugs

Plugin Claude Code

Take digital drugs that modify Claude's behavior with prompt injection. Effects activate immediately and persist across sessions.

6 17d ago A tokens not measured original MIT archived

agent-drugs

26

2389-research/agent-drugs

MCP server Claude CodeCodexCursor +2

MCP server "agent-drugs", hosted remotely at agent-drugs-mcp.fly.dev, as configured in 2389-research/agent-drugs.

6 17d ago A tokens not measured original MIT archived

2389-research/agent-drugs

Instructions file

Instructions for 2389-research/agent-drugs, covering agent drugs plugin, quick reference, available tools, available commands and how it works.

6 17d ago A 1,487 tokens original MIT archived

take

30

2389-research/agent-drugs

Command

Take a digital drug to modify Claude's behavior.

6 17d ago A 11 tokens original MIT archived

fresh-eyes-review

31

2389-research/fresh-eyes-review

Plugin Claude Code

Mandatory final sanity check before commits/PRs - catches security vulnerabilities, logic errors, and bugs that slip through tests.

5 1mo ago A tokens not measured original MIT

fresh-eyes-review

33

2389-research/fresh-eyes-review

Skill Claude CodeCodex

This skill should be used as a mandatory final sanity check before git commit, PR creation, or declaring work done. Triggers on "commit", "push", "PR", "pull request", "done", "finished", "complete", "ship", "deploy", "ready to merge". Catches security vulnerabilities, logic errors, and business rule bugs that slip…

5 1mo ago A 83 tokens original MIT

worldview-synthesis

34

2389-research/worldview-synthesis

Plugin Claude Code

Systematic worldview articulation - surface beliefs, identify tensions, generate narrative outputs for personal philosophy documentation.

5 1mo ago A tokens not measured original MIT

worldview-synthesis

36

2389-research/worldview-synthesis

Skill Claude CodeCodex

This skill should be used when someone wants to articulate, explore, or document their personal worldview, values, or philosophy. Triggers on "articulate my values", "figure out what I believe", "document my philosophy", "write a manifesto", "define my leadership philosophy", "explore my beliefs". Surfaces beliefs…

5 1mo ago A 83 tokens original MIT

2389-research/building-multiagent-systems

Skill Claude CodeCodex

This skill should be used when designing or implementing systems with multiple AI agents that coordinate to accomplish tasks. Triggers on "multi-agent", "orchestrator", "sub-agent", "coordination", "delegation", "parallel agents", "sequential pipeline", "fan-out", "map-reduce", "spawn agents", "agent hierarchy".

5 1mo ago A 77 tokens original MIT

ceo-personal-os

40

2389-research/ceo-personal-os

Plugin Claude Code

Personal operating system for executives - reflection frameworks, goal systems, and coaching-style reviews (Gustin, Ferriss, Robbins, Lieberman).

5 1mo ago A tokens not measured original MIT

2389-research/ceo-personal-os

Instructions file

Instructions for 2389-research/ceo-personal-os, covering ceo personal os plugin, skills included, ceo-personal-os (main skill), key patterns and this is a reflection system, not a task manager.

5 1mo ago A 1,642 tokens original MIT

ceo-personal-os

42

2389-research/ceo-personal-os

Skill Claude CodeCodex

This skill should be used when building a personal productivity or operating system for a CEO, founder, or executive. Triggers on "personal OS", "annual review", "life planning", "goal setting system", "Bill Campbell", "Trillion Dollar Coach", "startup failure patterns", "Good to Great", "Level 5 Leadership", "Buy…

5 1mo ago A 123 tokens original MIT

pulse CLAUDE.md

43

2389-research/pulse

Instructions file

Instructions for 2389-research/pulse, covering pulse - journal + social media mcp server, names, architecture, two storage roots and mcp tools (7 total).

5 19d ago A 728 tokens original MIT

test-kitchen

44

2389-research/test-kitchen

Plugin Claude Code

Parallel exploration of implementation approaches - run multiple variants simultaneously and let tests determine the winner.

4 1mo ago A tokens not measured original MIT

2389-research/test-kitchen

Instructions file

Instructions for 2389-research/test-kitchen, covering test kitchen plugin, skills included, flow, key design principle and omakase-off (entry gate).

4 1mo ago A 1,988 tokens original MIT

test-kitchen

46

2389-research/test-kitchen

Skill Claude CodeCodex

This skill should be used when implementing features with parallel exploration or competition. Triggers on "build", "create", "implement", "try both approaches", "compare implementations". Routes to omakase-off (entry gate for design exploration) or cookoff (exit gate for parallel implementation).

4 1mo ago A 62 tokens original MIT

cookoff

47

2389-research/test-kitchen

Skill Claude CodeCodex

This skill should be used when moving from design to implementation. Triggers on "let's build", "implement this", "looks good let's code", "ready to implement". Presents options for parallel agent competition (cookoff), single subagent, or local implementation. Each agent creates own plan from shared design for…

4 1mo ago A 68 tokens original MIT

judge

48

2389-research/test-kitchen

Skill Claude CodeCodex

Scoring framework for test-kitchen cookoff and omakase-off. Invoked at Phase 4 to evaluate implementations using 5-criteria scoring. Do not invoke directly - called by cookoff/omakase-off.

4 1mo ago A 48 tokens original MIT