ai-agents commands

5,539 tagged ai-agents, measured the same way as everything else here.

Browse within: agentic-ai 290claude-code-plugin 175ai-governance 157LLM 156agents 144cursor 136cli 125agents-md 123devops-tools 122architecture-decision-records 97architecture-governance 94arckit 90obsidian 82agent-framework 77

pr

25

TheDecipherist/claude-code-mastery

Command Claude Code

Generate a pull request description from branch changes.

not rated 554 +3 5mo ago A 8 tokens original MIT

oracle

26

evolution-foundation/evo-nexus

Command Claude Code

Use the @oracle agent. Oracle is the official entry point to EvoNexus — a business consultant that onboards users, interviews them about their business, maps workspace capabilities to their pain points, and delivers a phased implementation plan. Oracle orchestrates other agents (Scout, Echo, Compass, Clawdia, Bolt)…

not rated 547 +2 5mo ago A 0 tokens

pr-review

29

notque/vexjoy-agent

Command Claude Code

Comprehensive PR review using specialized agents, with automatic retro knowledge capture.

not rated 441 +1 changed 1mo ago A 13 tokens original MIT

release

30

bybren-llc/safe-agentic-workflow

Command Claude Code

Execute full version release — merge PRs, version bump, tag, GitHub Release, sync branches, cleanup.

not rated 423 2mo ago A 22 tokens original MIT

sync-branch

31

marcusquinn/aidevops

Command OpenCode

Sync session title with current git branch.

not rated 410 +2 today A 7 tokens original MIT

optimize

32

wesammustafa/opencode-primer

Command Claude CodeOpenCode

Suggest concrete performance improvements for the given file or directory.

not rated 402 +3 3mo ago A 10 tokens original MIT

upstream-watch

33

DougTrajano/pydantic-ai-skills

Command Claude Code

Review pydantic-ai and pydantic-ai-harness releases published since the last watch entry, and record a verdict in .github/upstream-watch.md.

not rated 379 +1 changed 1mo ago A 31 tokens original MIT

notify

34

autonomous-ai/autonomous-os

Command Claude Code

Send a notification to your device.

not rated 378 11d ago A 6 tokens original Apache-2.0

metis

35

Wholiver/metis

Command Claude Code

A controlled command for starting Metis work through an external controller. It selects a route from the recorded request and manages worker dispatch and recovery; it does not activate during ordinary coding or review requests.

not rated 369 +37 today A 28 tokens original MIT

OPSX: Explore

36

theexperiencecompany/gaia

Command Claude Code

Enter explore mode - think through ideas, investigate problems, clarify requirements.

not rated 312 +4 today A 18 tokens

pwf-doc

37

J-Pster/Psters_AI_Workflow

Command Claude Code

Documentation command. Modes: (1) /pwf-doc lambda — Lambda doc, (2) /pwf-doc lambdas — all Lambdas, (3) /pwf-doc module — backend module doc, (4) /pwf-doc feature — frontend feature doc, (5) /pwf-doc architecture — system architecture overview, (6) /pwf-doc update — scan all docs for staleness and contradictions, (7)…

not rated 289 7mo ago A 161 tokens original MIT

meta-theory

38

KimYx0207/Meta_Kim

Command Claude Code

Run the MetaKim meta-theory governance dispatcher.

not rated 283 today A 10 tokens original Apache-2.0

prun

39

yzhao062/anywhere-agents

Command Claude Code

Run prun: parallel delegation fan-out on Agy workers (the session coordinates).

not rated 257 +6 changed 1mo ago A 17 tokens original Apache-2.0

slm-remember

40

qualixar/superlocalmemory

Command GitHub Copilot

Capture durable facts, decisions, constraints, and gotchas into SuperLocalMemory. Use when the user says "remember that", "save this decision", "note this constraint", or when a session produces a conclusion worth persisting across sessions. Always recall first to avoid duplicates.

not rated 241 +11 changed today A 60 tokens AGPL-3.0

synthesize

41

ProjectDXAI/labrat

Command Claude Code

Synthesize what the recent evaluations mean before dispatching more work. This step closes the gap between "config sweeper" and "research agent.".

not rated 237 +1 2mo ago A 0 tokens original MIT

phase-review

42

olo-dot-io/Uni-CLI

Command Claude Code

Review a phase's worktree against the spec before merging into main.

not rated 235 +39 3d ago A 0 tokens original Apache-2.0

greet

43

weijiafu14/pi2dsh

Command Claude Code

Reply with exactly the text GREET-COMMAND-OK and nothing else.

not rated 216 +4 2d ago A 3 tokens original MIT

context

44

VAMFI/claude-user-memory

Command Claude Code

Analyze and optimize context configuration. Reviews CLAUDE.md, knowledge-core.md, and active context for optimization opportunities. Helps prevent context rot (39% improvement, 84% token reduction).

not rated 212 +1 20d ago A 40 tokens

clean

45

OWWZO/ai-agent

Command Claude Code

Clean up old Answer me with HTML pages, videos and the narration cache.

not rated 195 +7 6d ago A 14 tokens

coleam00/dark-factory-experiment

Command Claude Code

Holdout-pattern E2E validator. Drives agent-browser against the running DynaChat app to verify that the PR's user-facing behavior actually matches what the linked issue asked for.

not rated 170 +2 2mo ago A 36 tokens

stop

48

mtarcure/claude-vibe-squad

Command Claude Code

Gracefully close the Vibe Squad tmux session from inside Chrono.

not rated 165 25d ago A 0 tokens original MIT

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: