~ / leaderboard / subagent / audit
Subagent · #508
audit
Verify-band role of a /cc-orchestrate run. Reviews the item's changes statically against its spec and plan, read-only, and hands back build_executed with its findings. No shell. Dispatched only by /cc
5rigs use it
0%of all rigs
18.6kavg rig context tax
Get it
$ npx degit tonone-ai/tonone/agents .claude/agents From the most-starred rig that ships it: tonone-ai/tonone. Same-named subagents in different rigs may differ — review before use.
Often used together with
grill-with-docs · 1Playwright MCP · 1Context7 · 1agent · 1termlink · 1systematic-debugging · 1researcher · 1orient · 1wrap · 1review-queue · 1
Rigs using audit (5)
tonone-ai/tonone
One session. Two commands. Full team. Zero meetings.
Orchestrator 11.9k tok · · Q0
DimitriGeelen/agentic-engineering-framework
Governance framework for AI coding agents — enforces task traceability, structural gates, session continuity, and audit trails for Claude Code, Cursor, and Copilot.
Orchestrator 57.3k tok · · Q25
jimy-r/agent-workspace-architecture
Agent-ready knowledge architecture, run daily in Claude Code: turn a coding agent into a system you can hand work to and trust while you're away. 18 load-bearing patterns, one-page workspace map, interactive tour, guided learn track, teardo
Orchestrator 2.8k tok · · Q8
yeisonrestrepo/code-conductor
A governance layer for Claude Code sessions: hooks that check an agent's commands before they run, a spec-first workflow, and project memory the next session reads.
Orchestrator 6.1k tok · · Q51
Remus3/Amberstone
Local real-time coaching for League of Legends and Teamfight Tactics. A deterministic engine does the item and damage math from the game's own numbers, and the AI coach only narrates what that math already decided. No win-rate scraping.
Orchestrator 14.7k tok · · Q8