autonomous agents commands

the-open-engine/zeroshot

Command Claude Code

Postmortem analysis of cluster failures → OPTIMIZE PROMPTS to work for EVERY use case.

evo-hq/evo

Command

Discover what to optimize and initialize an evo workspace.

evo-hq/evo

Command

Run the evo autoresearch optimization loop.

najmuzzaman-mohammad/gawkbot

Command

List entity briefs and workspace playbooks, or view a specific brief.

najmuzzaman-mohammad/gawkbot

Command

List agent skills, view a skill, compile, or sync to local folder.

ltjed/freephdlabor

Command Claude Code

You are tasked with analyzing agent instructions from the agent's perspective to evaluate whether they have sufficient information, context, and clarity to successfully perform requested tasks.

ltjed/freephdlabor

Command Claude Code

You are tasked with optimizing the multi-agent workflow by iteratively improving agent instructions to produce high-quality papers publishable at top AI conferences.

ruvnet/metaharness

Command Claude Code

Health-check the harness: kernel load, MCP wiring, memory backend, host adapter.

ruvnet/metaharness

Command Claude Code

Review the current working diff for correctness, security, and reuse.

ZhixiangLuo/10xProductivity

Command Claude Code

Search institutional knowledge across every connected tool simultaneously.

ZhixiangLuo/10xProductivity

Command Claude Code

Connect any tool you use at work — internal company tools, custom-built systems, and commercial tools like Slack, Confluence, Jira, Linear, GitHub, Outlook, Datadog, and PagerDuty.

jayminwest/warren

Command Claude Code

Prepare, cut, and verify a warren release — tracker audits, version bump, CHANGELOG curation, ROADMAP update, push, then watch the pipeline through to published artifacts.

automagik-dev/genie

Command Claude Code

Assess your Claude Code level (0-10) and get a personalized roadmap to the next one.

automagik-dev/genie

Command

Assess a proposal through independent technical, product, risk, and dissenting lenses, then synthesize a decision without mutating unless explicitly requested.

automagik-dev/genie

Command

Investigate bugs comprehensively — cascade through /genie:trace, capture browser evidence, extract observability data, and prepare or explicitly create a GitHub issue with grounded findings.

Sibyl-Research-Team/AutoResearch-SibylSystem

Command

A reference document for an orchestration loop, meaning the repeated process used to coordinate a system's steps. The live control protocol is generated dynamically at runtime.

Sibyl-Research-Team/AutoResearch-SibylSystem

Command

Command "continue" from Sibyl-Research-Team/AutoResearch-SibylSystem, covering /sibyl-research:continue and 步骤.

Sibyl-Research-Team/AutoResearch-SibylSystem

Command

A debugging command that runs an orchestration loop one step at a time.

AIOSAI/AIPass

Command Claude Code

Purpose: Capture the decision just made into compass (the rated decision engine) with the user's rating and note. The user fires this when they notice a decision worth recording — they supply the judgement, you supply the decision text from the conversation. This is the human-triggered answer to the "noticing"…

AIOSAI/AIPass

Command Claude Code

Purpose: Button up everything at the end of a session — or before a /compact. Memories, plans, git — all tidy. Works for both closing out a chat and preparing for compaction.

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).

VAMFI/claude-user-memory

Command Claude Code

Quick command to invoke code-implementer to execute implementation with self-correction (up to 3 intelligent retries).

VAMFI/claude-user-memory

Command Claude Code

Complete Research → Plan → Implement workflow in one command. Invokes chief-architect to orchestrate all phases with quality gates and self-correction.

coleam00/dark-factory-experiment

Command

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.