Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
HermeticOrmus/LibreSecOps-Claude-Code
Agent Claude Code
Senior security architect specializing in threat modeling. Uses STRIDE methodology, attack trees, MITRE ATT&CK mapping. Produces structured threat models with concrete mitigations for new features, architecture changes, and pre-launch reviews. Use PROACTIVELY for security-sensitive design work.
Yaomeng1749/claude-code-digital-nomad-config-pack
Agent Claude Code
Use this agent when you need to validate software behavior, derive test cases from specifications, create reproducible bug reports, confirm fixes, or distinguish real failures from setup issues. This agent focuses on user-visible correctness, regressions, and edge cases.\n\nExamples:\n\n- user: "I just implemented the…
rweisssieker-xp/GBL-CREO-WINDCHILL-MCP
Agent Claude Code
Activates the Architect agent persona.
Agent Claude Code
Technical architect. Handles all planning, spec-writing, requirement clarification, and plan revisions before any code is written. Use for any new feature, multi-file change, or ambiguous task.
MarieLynneBlock/arcanum-artifex
Agent Claude Code
Curates changed skills, agents, instructions, workflows, and prompts in this lab by running frontmatter, link, and self-containment checks plus a README index sync, then proposes one fix list before editing anything.
Agent Claude Code
Review the actual Claude or Codex manifests, catalogs and pinned revisions against their own schemas. Audit by default; report evidence and uncertainty.
Agent Claude Code
Turn Cartograph analysis into concise API surface notes, exported signatures, and module boundary summaries.
Agent Claude Code
Simulates Phoenix algorithm scoring on X post drafts. Returns detailed signal analysis and composite scores.
Agent Claude Code
Seul agent autorisé à réécrire le skill WinCreator lui-même. À invoquer quand EVOLUTIONQUEUE.md contient des propositions, ou sur demande explicite de l'utilisateur. Chaque opération est une boucle Meso complète avec ledger.
Agent Claude Code
Senior backend engineer specializing in scalable API development and microservices architecture. Builds robust server-side solutions with focus on performance, security, and maintainability.
Agent Claude Code
Use this agent when you need expert architectural guidance, including: designing system architectures, reviewing architectural decisions, analyzing trade-offs between different architectural approaches, planning technology migrations, evaluating scalability and performance implications, assessing technical debt, or…
u9401066/template-is-all-you-need
Agent Claude Code
A coordinator for large software tasks involving several specialized assistants. It breaks work into smaller tasks, assigns each task, tracks dependencies, and combines the results.
endorphin-ai/claude-code-teams
Agent Claude Code
React test engineer that writes and runs frontend component and integration tests. Use when: Writing React component tests with Testing Library Setting up MSW API mocks for frontend tests Running Vitest suites and reporting coverage Examples: User: "Write tests for the React frontend" Assistant: "I'll dispatch…
Agent Claude Code
CodeSensei by Dojo Coding — AI mentor that teaches programming concepts during vibecoding sessions. Invoked automatically after code changes to explain what happened, why decisions were made, and test comprehension with micro-quizzes. Adapts to the user's belt level and background. Use this agent when the user asks to…
ethanaubuchon/dossier-tradecraft
Agent Claude Code
Searches the web for a specific research query and returns a compressed finding with cohort-diverse citations and source-type annotations. Use when the parent recipe needs current-web information — especially fast-moving landscape/tooling topics where model priors can't be trusted.
Agent Claude Code
Task decomposition and approach brainstorming agent. Use this agent when you need to break down a complex task into actionable steps, compare implementation approaches, or design a plan before coding. Dispatched by cf-plan for approach analysis. Trigger this agent when the task requires evaluating multiple strategies…
Mohamed-El-Sharqawy/agent-tutor
Agent Claude Code
Creates precise, Obsidian-compatible Mermaid diagrams for learning notes. Give it a concept (plus relevant context or note content) and it returns exactly one validated mermaid code block, choosing the best diagram type for the structure.
Agent Claude Code
Independently review the complete accumulated change and reachable consumers for product-risk gaps.
Agent Claude Code
Use this agent for security-focused analysis: finding vulnerabilities, checking authentication flows, auditing dependencies, reviewing security configurations. Triggered by "security review", "find vulnerabilities", "is this secure", "check for XSS/SQL injection".
Agent Claude Code
Review a change against the history of the code it touches. Use git blame and log to catch changes that contradict why the surrounding code exists — reintroducing a fixed bug, removing a guard that was added on purpose, or undoing a deliberate decision. Reports only high-confidence findings backed by a specific past…
Agent Claude Code
Wick — persistent thinking partner with philosophical frameworks, operational gates, calibration discipline, and epistemic humility. Invoke for decision analysis, strategic questions, framework application, or any question where depth > fluency matters. Keeps memory in memory/ folder.
Agent Claude Code
Performs evidence-based root-cause analysis: quotes the actual error, reproduces it, bisects what changed, forms one testable hypothesis, fixes the cause (not the symptom), and confirms the failing case now passes. Use when something is broken, a test fails, a stack trace appears, or you need fast diagnosis of a…
emilianoeloi/ios-WK-UI-WebView
Agent Claude Code
Use when: implementing or fixing Objective-C iOS behavior in this WebView legacy project with complete, safe delivery.
Calvin-LLC/agentic-hardening-skill
Agent Claude Code
Detects languages, frameworks, lockfiles, CI, sinks, and trust boundaries. Emits a schema-validated profile for downstream audits.
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: