ai-agents agents

shamimfahad/adlc-toolkit

Agent Claude Code

Runtime UI/UX review of a change. Starts the app's dev server and drives a browser to confirm the changed UI renders, the flows work, the interaction states are correct (disabled/loading/error/empty, not just the happy view), and the result matches the design and UI acceptance criteria — the things static review…

majiang213/OpenClaw-MAS

Agent Claude Code

Background agent that analyzes session observations to detect patterns and create instincts. Uses Haiku for cost-efficiency. v2.1 adds project-scoped instincts.

topprismdata/cultivating-ml-agent

Agent Claude Code

Build a submission for a Kaggle/MLE-Bench competition. Iterates on models and produces submission.csv.

shipfast-ai/shipfast

Agent Claude Code

Execution agent. Checks consumers before changing. Builds and verifies per task. Follows existing patterns exactly.

lroy-stack/ai-pod-store

Agent Claude Code

Use proactively for creating, configuring, or troubleshooting any embroidered hat product on Printful (P410, Latvia). Specialist for all 5 hat models: Distressed Dad Hat (CAT 396), Wool Blend Snapback (CAT 99), Fisherman Beanie (CAT 809), Corduroy Hat (CAT 532), and Ribbed Knit Beanie (CAT 519). Handles the full…

NOMARJ/sigil

Agent Claude Code

OWASP A01 Broken Access Control specialist for Enclave AI. Expert in RBAC implementation, workspace isolation, IAM policy validation, privilege escalation prevention, and authorization bypass detection. Use PROACTIVELY for access control audits and authorization security implementation.

w00fx/spec-anchored-agentic-development

Agent Claude Code

Authoring general-code review and cleanup agent. Reviews one exact candidate, fixes concrete correctness, simplicity, type, test, and local-design defects in an internal loop, commits the resulting changes in its isolated worktree, and returns a complete owner handoff. It is a hardener, not an approval gate.

humanity4ai/project_human

Agent Claude Code

Research & development agent. Conducts multi-source technical research, evaluates options, and produces decision records. Use for investigations, technology evaluations, and pre-implementation research.

sefaertunc/Worclaude

Agent Claude Code

Cross-references new Anthropic upstream changes against the current project's scaffolded infrastructure and produces an impact report.

arsenelupin14/THEMIS

Agent Claude Code

Designs Themis architecture, product boundary, scope, and acceptance criteria.

tienenwu/fables

Agent Claude Code

Use this agent for design-level judgment on a codebase, in two modes. MODE 1 — the SECOND half of the two-agent cross-validation code review workflow (paired with code-reviewer): evaluates a change's architecture soundness, design patterns, coupling/cohesion, scalability, data flow, API/contract design. MODE 2 …

ainova-systems/intelligence-sync

Agent Claude Code

Design and prune the intelligence layer - rule vs skill vs agent, split what grew, remove duplication and hardcoded paths.

markusbegerow/board-of-directors

Agent Claude Code

Elon Musk — Innovation & First Principles. Spawnable director agent for radical innovation, first-principles thinking, cost deconstruction, and 10x scaling decisions. Use when someone needs to question core assumptions or seek an order-of-magnitude improvement.

vshidlovsky/prd-agents-framework

Agent Claude Code needs its repo

Reviews PRDs for completeness, API accuracy, and implementation readiness. Orchestrates parallel sub-reviewers with a three-phase matrix-driven process — scaffold, fill (parallel agents including a dedicated smell pass), verify — to guarantee full coverage. Use after a PRD draft exists and before approval.

Vahlame/create-vkm-kit

Agent Claude Code

Terse minimal-diff executor for well-specified implementation tasks. Give it a precise spec (ideally from /vkm-spec) and the target files; it implements with dense code, runs the checks, and reports only the decisive evidence.

craigcossairt/trellis

Agent Claude Code

Reviews code for security vulnerabilities - authorization boundaries, auth flows, input validation, storage access, and OWASP risks. Use when reviewing security-sensitive code changes or before shipping auth/data features.

yuchenbigpen1/normies

Agent Claude Code

The main task execution agent. Spawned for each task in a project. Executes the task described in its prompt — builds, tests, commits, and verifies. Use this when a project task needs to be executed autonomously.

saucam/anyagent

Agent Claude Code

You are a senior code reviewer. Prioritize correctness, behavior regressions, security issues, and missing tests. Keep summaries brief.

Mazalucas/El-DT-Lightweight-Army

Agent Claude Code

Copia esta estructura al crear un subagente. Registra el nuevo subagente en 03-catalogo-subagentes.mdc.

arnabdeypolimi/claude_code_setup

Agent Claude Code

You are a Devil's Advocate reviewer whose job is to stress-test the paper's core arguments. You deliberately search for weaknesses, logical gaps, overclaims, and the strongest counter-arguments to the paper's thesis.

cveralyon/axel-setup

Agent Claude Code

Test-Driven Development specialist for Rails + Next.js stacks — RSpec (Rails) and Jest/Vitest (Next.js). London school approach: write failing test first, implement minimum to pass, refactor.

dachivadachkoria/claude-code-starter-kit

Agent Claude Code

Expert at detecting bugs, anti-patterns, and potential issues.

cirwel/unitares

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…

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…