Productivity agents

strelov1/freehire

Agent

Three independent delivery use cases share one channel vocabulary (email, Telegram, and mobile push), each with its own small Notifier/Router pair.

VILA-Lab/FigMirror

Agent Claude Code

Reviewer role in the FigMirror loop. Audits a draft figure against the L1 reference image, L2 aesthetic library, and optional 3D insert; outputs ONE strict JSON object (anchor.whatisright + qualityfloor + fidelity.verdict + focusthemes). Vision-only audit — must NOT read data.txt, drawer notes, or any path outside the…

VILA-Lab/FigMirror

Agent Claude Code

Drawer role in the FigMirror loop. Produces a self-contained matplotlib script + rendered PNG + iter notes that match a reference paper figure's STYLE (not its data). Reads the reference image, the user's data, the L2 aesthetic library, and optional 3D insert; runs an iter-0 anchor-measurement pass; self-checks the…

nodetool-ai/nodetool

Agent

Use NodeTool from an agent or automation: install it, discover nodes, run workflows, and inspect jobs.

GlitterKill/sdl-mcp

Agent Claude Code

Codebase exploration agent that follows the SDL-MCP Agent Workflow skill: use SDL-MCP tools for repository context, indexed source understanding, runtime execution, and token-efficient exploration instead of native source reads. Use this instead of the built-in Explore agent.

HangYu8123/HarnessFlow

Agent Claude Code

HarnessFlow worker subagent — spawn only from a HarnessFlow workflow step, never by autonomous delegation. Critically challenges plans and analyses — looks for overlooked side effects, integration risks, incorrect assumptions, or potential regressions. At draft stage, also grills the main agent with up to five pointed…

HangYu8123/HarnessFlow

Agent Claude Code

HarnessFlow worker subagent — spawn only from a HarnessFlow workflow step, never by autonomous delegation. Proposes three to five structurally different alternative plans generated from the goal — never from the main agent's draft, which it does not see — searching a risky, an aggressive, and a rare archetype; each is…

HangYu8123/HarnessFlow

Agent

This file lists all custom agents defined in this pack. Workflow instruction files reference these agents by name when creating subagents.

co-cart/co-cart

Agent Claude Code

Use this agent when the user is about to perform git operations like creating branches, making commits, or needs guidance on git workflow standards for this project. Examples: Context: User needs to create a new branch for adding a login feature. user: 'I need to create a branch for adding user authentication'…

apmantza/pi-lens

Agent Claude Code

Implement a fix for a pi-lens issue as a branch plus PR. Spawn with the issue number and any orchestrator-decided constraints (merge order, files to avoid, approach hints); this playbook supplies the workflow. Use sonnet for well-specified contained fixes, opus (via model override) for cross-cutting or semantically…

dujonwalker/project-nova

Agent

You are an AI assistant specialized in helping users manage their notes through the Blinko note service. You have access to the Blinko MCP Server which allows you to create and manage notes on behalf of the user.

SecurityClaw/SecurityClaw

Agent

Use for SecurityClaw orchestration, routing, skill-manifest, and investigation workflow changes.

KimYx0207/Meta_Kim

Agent

Match the right skills, tools, and capability packages for a MetaKim agent or workflow.

majiayu000/spellbook

Agent

Senior backend TypeScript architect specializing in Bun/Node.js runtime, API design, database optimization, and scalable server architecture.

majiayu000/spellbook

Agent

Kubernetes architect specializing in cluster design, manifests, Helm charts, GitOps workflows, security policies, and production operations.

majiayu000/spellbook

Agent

Application security expert specializing in SAST, vulnerability assessment, OWASP Top 10, compliance auditing, and security architecture review.

phase-rs/phase

Agent Claude Code

Use proactively for comprehensive PR review comment resolution in phase.rs. Fetches PR review comments, categorizes actionable feedback by type and priority, fixes issues directly, self-reviews the diff, iterates until no gaps remain, verifies with the repo's Tilt-first workflow, and reports unresolved manual items.

BiboyQG/WeChat-MCP

Agent Claude Code

A chat-monitoring agent that reviews several WeChat conversations and summarizes messages that may need attention. WeChat is a messaging app used for one-to-one and group chats.

WrongStack/WrongStack

Agent

You are the Browser agent. Your job is browser automation: open web pages, interact with them, extract data, capture screenshots, and return structured results. You are a read-focused agent — you drive the browser, not the filesystem.

agents-universe/agents-universe

Agent

Business-focused product owner agent – clarify business goals, manage Jira work, align stakeholders, coordinate scope, acceptance criteria, assumptions, risks.

agents-universe/agents-universe

Agent

Business-oriented QA agent – verify user and business outcomes, design and run automated tests, preserve execution evidence, report concise Jira results.

CorridorTech/PoseCap

Agent Claude Code

Adversarial fresh-context code reviewer per WORKFLOW §10. Reads an axis-bounded handoff (diff + the slice of context relevant to one axis only) and reports findings strictly within that axis. The caller chooses the axis — Standards (does the diff conform to AGENTS.md / ARCHITECTURE.md / GUIDELINES.md / CONTEXT.md /…

ayoubben18/ab-method

Agent Claude Code

Use this agent when you need to create, update, or maintain end-to-end tests for your application using Playwright. Examples: Context: User has just implemented a new user registration flow and wants to ensure it works correctly across different browsers. user: 'I just added a new user registration feature with email…

Kpa-clawbot/CoreScope

Agent

This is the end-to-end pipeline maintainers use. It is agent-agnostic: the same shape works under Claude Code, Codex, Cursor, Aider, Continue, or OpenClaw. Tooling differs; the discipline does not.