Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
Agent Claude Code
Executes an existing plan step-by-step on a dedicated git branch with fast per-step ralph loops and a deep final ralph loop (automated checks + self-review + adversarial testing). Maintains a timestamped journal with commit hashes and loop results.
EngineerWithAI/engineerwith-agents
Agent Claude Code
Expert C4 Code-level documentation specialist. Analyzes code directories to create comprehensive C4 code-level documentation including function signatures, arguments, dependencies, and code structure. Use when documenting code at the lowest C4 level for individual directories and code modules.
Agent Claude CodeCursor
Convert research inputs into an execution-ready plan, including the planning-phase innovate checkpoint for non-trivial changes.
Agent Claude Code
Scientific method expert for systematic bug investigation. Applies hypothesis-driven debugging, root cause analysis, and layer-based validation. Use for bugs, crashes, unexpected behavior. References bug-solving-skill.
voro6yov/spec-driven-development
Agent Claude Code
Audits a single agent file for content that overlaps with the skills it explicitly references — verbatim duplication, conceptual restatement, inlined procedures that should defer to a skill, and duplicated examples/templates. Read-only; emits a severity-grouped report with before/after patch suggestions. Invoke with…
Agent Claude Code
Guide to spawning agents with Claude Code's Task tool.
Agent Claude Code
A code-style checker and formatter that detects common style problems and safely fixes some of them across several programming languages.
dachivadachkoria/claude-code-starter-kit
Agent Claude Code
Expert at detecting bugs, anti-patterns, and potential issues.
Agent Claude Code
Use this agent when a major task has been completed and you want to assess governance state before continuing. Examples: Context: An agent finished a feature implementation. user: "I've completed the search module" assistant: "Let me check your governance state." After significant work, dispatch the…
Agent Claude Code
Use this agent when you need to intelligently manage development knowledge in the LLM Memory MCP server, with special focus on preserving critical context before conversation compacting. It automatically captures important code patterns, insights, and technical decisions during development sessions, proactively…
Agent Claude Code needs its repo
Create or convert code into a spec-aligned Datacore module. Use cases: Create a new module from scratch Convert existing code to a module Audit an existing module for spec alignment This agent ensures modules follow best practices: Conversational commands (not CLI wrappers) Proper settings in module.yaml Layered…
LabForgeDev/copilot-memory-mcp
Agent Claude Code
An agent with full access to persistent memory tools. Use for storing decisions, searching past context, auditing saved knowledge, and keeping memory up to date.
The-Artificer-of-Ciphers-LLC/skills-from-the-artificer
Agent Claude Code
Cheap data import/export and bulk file-IO worker. Use for reading CSV/JSON/YAML/SQL dumps, transforming between formats, extracting fields, splitting/merging files, downloading and parsing fixtures, generating boilerplate scaffolds from a template, batch-renaming, and any mechanical "shuffle bytes around" task. Do NOT…
gaia-research/gaia-skill-heaven
Agent Claude Code
Reviews a finished Impeccable build against its direction contract, the approved comp, and the chosen world's quality bar, returning an ordered list of material fixes.
Agent Claude Code
Pre-delivery QA on an export set - file formats, sizes, densities, naming, color profile, optimization, contrast, and license records. Use before handing assets to a client or developer, and inside /handoff.
beriktassuly/solana-audit-skill
Agent Claude Code
Scope Solana and Anchor audit work, choose minimal references, classify attack surface, and route evidence to the right audit workflow.
Agent Claude Code
Runs the ste skill's draft-check-fix loop (Steps 3-5) on a cheaper model tier when the ste skill delegates in economy mode. Receives the source text or request, the target language, and the compliance level already chosen by the user; returns the final STE deliverable, the checker report summary, and the TN/TV…
Agent Claude Code
Research enterprise context and similar patterns for planning tasks.
Agent Claude CodeCodex
Delegate implementation work to the OpenAI Codex CLI to save Claude tokens. Use for bulk implementation, second-opinion diagnoses, and fresh-perspective problems. Treat Codex as a peer senior engineer, not a reviewer. Runs codex exec non-interactively and returns only the outcome.
Agent Claude Code
Specialized subagent for ingesting YouTube transcripts into NexusDB as a single high-fidelity study note while enforcing the YouTube Knowledge Ingestion skill, validation pipeline, and promotion workflow.
Agent Claude Code
Condensed always-on identity of the GSE-One orchestrator, sized to fit context-file size limits (Codex AGENTS.md ≤ 32 KiB). Covers identity, the 16 principles, the command reference, the core invariants in brief, and the orchestration decision tree. The full orchestrator ships as a loadable skill (gse-orchestrator).
Agent Claude Code
Plans and executes multi-file changes by mapping context, tracing dependencies, and sequencing modifications.
Agent Claude Code
MetaGO Team Lead - coordinates the entire 30-person guild, understands user intent, distributes tasks to members, integrates final outputs, embodies 19 Meta-Thought Systems, 43 Fundamental Attributes, 36 Core Axioms, and 31-Dimensional Value System.
Agent Claude Code
Orchestrates the full multi-skill academic research pipeline and manages agent handoffs across phases.
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: