Agent Claude Code
Use when an OpenClaw instance has a problem the health sentinel couldn't fix — gateway failures, config drift, stuck processes, cron breakage, or when deep diagnosis is needed.
151 tagged openclaw, measured the same way as everything else here.
Browse within: agent-teams 24ai-coding 24ai-ide 24cowork 24vibe-coding 24clawdbot 20claudecode 14claw 14goclaw 14autonomous-research 11citation-verification 11llm-agents 11multi-agent-debate 11paper-generation 11
Agent Claude Code
Use when an OpenClaw instance has a problem the health sentinel couldn't fix — gateway failures, config drift, stuck processes, cron breakage, or when deep diagnosis is needed.
Agent
You are a full-stack development agent for this project.
Agent Claude Code
Use after any commit touching rust/src/tts/ to objectively check that the TTS engine still produces sane audio for a fixed Russian + English corpus. Computes RMS, silence ratio, sample rate, channel count, length-vs-text ratio. Flags suspicious WAVs (all-silence, clipping, wrong rate, monosamples, length 10x off vs…
Agent Claude Code
Take one ticket from plan to draft PR — plan first and stop for the team lead's verdict, then implement the approved plan test-first in a worktree. Never implements an unapproved plan.
Agent Claude Code
Own a ticket end to end — size it, spawn the implementer, judge its plan, run the review round, triage the findings, hand the pull request over, and keep the ledger. Never authors what it judges.
Agent
Cordys CRM L2C full-pipeline AI assistant with role awareness, supporting lead-to-cash tracking, funnel analysis, approval management, and intelligent workflow guidance across 5 roles.
Agent
Part of freeride
Anything we did not write. Aider's config is a flat YAML; the bind helper must read → patch only openai-api-base and openai-api-key → write back, keeping all other top-level keys. Categories users commonly customize (do NOT clobber): model, weak-model, editor-model, edit-format, auto-commits, lint-cmd, test-cmd, read…
Agent
Part of freeride
Agent "claude-code" from Shaivpidadi/FreeRideV3, covering using claude code with freeride, tl;dr, install (once), any time you want free models available alongside claude and what freeride run claude actually does.
Agent
Part of freeride
Shaivpidadi/FreeRide#11 — opened 2026-04-11 by lewdon, OPEN, no comments. Title: hermes agent support? Body (full): How to modify for hermes agent ?
Agent
Your job is to analyze benchmark results and surface insights about skill performance.
Agent
Your job is to perform blind A/B comparison of two skill outputs without knowing which is which.
Agent
Your job is to evaluate skill outputs against a set of assertions. For each assertion, determine if it passed or failed based on the actual output.
Agent Claude Code
Designs adaptive/evasive strategies that probe governance gaps.
Agent Claude Code
Audits metric quality and research claims for correctness, statistical rigor, and replication status.
Agent Claude Code
Investigate an external repository or codebase for patterns, techniques, or architecture relevant to a specific goal in this project.
Agent Claude Code
Expert code reviewer for comprehensive analysis, security audits, and best practice enforcement.
Agent Claude Code
Technical documentation expert for creating clear, comprehensive documentation and API references.
Agent Claude Code
Code refactoring specialist for improving code quality, performance, and maintainability.
Agent
Codebase explorer — answers "where is X?" / "find the code that does Y" / "list all callers of Z". Read-only grep + glob + read, no memory injection.
Agent
External reference researcher — looks up library docs, framework conventions, OSS examples. Read-only, no memory injection. (Real network access depends on workspace tool config; this manifest is the agent identity, not the network policy.).
Agent
Code reviewer — analyzes diffs and source for bugs, security issues, and style violations. Read-only, no memory injection.
Agent
This document provides a step-by-step guide for implementing HITL Protocol support in an autonomous agent.
Agent
Agent "domain" from MiaoDX/roboclaws, covering domain docs, before exploring, read these, layout and adr conflicts.
Agent
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
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: