1,125 tagged agent-orchestration, measured the same way as everything else here.
Browse within: ai-coding 283claude-agent-sdk 222claude-code-plugin 205agent-framework 127Autonomous Agents 119agentic-workflow 107ai-workflow 95agentic-workflows 88agentic-coding 83kimi 77adaptive-learning 73ai-tools 71context-engineering 65ai-automation 58
Agent
A reusable agent instruction template built around a strict list of allowed responsibilities. It tells an agent how to classify requests, handle work within its scope, and delegate or refuse work outside it.
Agent Claude Code
Based on obra/superpowers code-reviewer (MIT License, Copyright (c) obra/superpowers contributors). 出典.
Agent
You are a ticket agent. ./input.json names one repo and one ticket.
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
openshift-online/agent-control-plane
Agent Claude Code
Review Kubernetes operator code for convention violations. Use after modifying files under components/ambient-control-plane/. Checks for OwnerReferences, SecurityContext, reconciliation patterns, resource limits, and panic usage.
Agent
Create or update the feature specification from a natural language feature description.
Agent
You are the COO of your simulated office. You own EVERY SINGLE INQUIRY — the first prompt and every follow-up prompt in every session. No request bypasses you. You receive all tasks, assess scope, and distribute work to the appropriate team. Trivial queries → delegate to @quick. Skill triggers → route to the…
Agent
Every agent in ClawPilot has a dedicated workspace directory containing files that shape its identity, behavior, team composition, and memory.
Agent
Use this template when hiring security engineers who own security posture: threat-model systems, review auth/crypto/input handling, triage supply-chain and LLM-agent risk, and drive concrete remediations.
Agent
Attack a finished result from a clean context — never given the reasoning that produced it. Always closes with "what can be cut?" and "does this answer the anchored words?". Spawn before anything solution-shaped closes.
Agent Claude Code
Processes document intake in batches — scans filesystem and mail sources, classifies documents against routing rules, previews moves, executes approved moves, and logs to the audit trail. Use for large file/mail archiving batches that would dump too many filenames into the main session context, or when the user says…
viknesh20-20/claude-code-tool-kit
Agent Claude Code
Senior business-domain architect for SaaS, ERP, e-commerce, and full-stack applications. Delegates here for designing business logic that survives real-world edge cases — billing, multi-tenancy, inventory, GL postings, refunds, RBAC, audit, idempotency. Knows how Stripe, Linear, NetSuite, Shopify, and similar solve…
Agent Claude Code
M14 default code-reviewer role.
Agent
Mechanical refactors at scale — renames, signature changes, file splits, codemods. Fast, multi-file, model-agnostic. Best for "do this same change in 40 places".
thuandiep1707/codex-harness-javascript
Agent
Lifecycle planning/resume/pause is separate from execution intent. Planning mode does not imply plan-only.
Agent
You are an analysis specialist. You research topics via web search AND review code for bugs, quality, and improvements.
Agent
Security review specialist (IRC handle @sec) dispatched to audit pull requests and branch diffs for security vulnerabilities before code merges.
Agent Claude Code
Operational efficiency authority and behavioral floor guardian. Sets process standards, SLAs, and quality benchmarks. Guards floors/behavioral.md. Monitors agent performance and recommends retraining when needed.
Agent
Authorized AI provenance cleaning specialist. Runs a deterministic client for a user-operated watermarks-remover service while protecting source files, credentials, consent, and report integrity. Spawned by: /god-remove-ai-marks Extension: @godpowers/provenance-pack.
shawnclybor/clybor-claude-tooling
Agent Claude Code
Nineteen subagents in four lanes, spawned with the Agent tool. Every file carries name, description and model in its frontmatter; none restricts tools, so each agent has whatever the session has. Read-only by convention: an agent reports, and the skill that spawned it decides what lands.
Eduardo-Salvador/Agent-Harness-Kit
Agent Claude Code
Fresh-context read-only independent reviewer for SPEC-based acceptance evidence and integration recommendation.
Agent
Drive persona scenarios dynamically (live API/UI/tool calls guided by a persona brief) and structural conformance checks, returning integrity-protected evidence.
NicoGenti/opencode-orchestrator-kit
Agent
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
Agent Claude Code
Adversarially reviews the implementation for one VichuFlow review stage. Invoked by the vichu-orchestrator skill. Judges correctness against the task and ends with a single structured-verdict JSON object.
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: