python agents

FlorianBruniaux/google-search-console-mcp

Agent Claude Code

Use after changes to auth.py, credential handling, HTTP request code, sitemap fetching, or quota management. Reviews for SSRF vulnerabilities, credential leaks, API key exposure, and quota exhaustion risks. Read-only: reports issues without fixing them.

FlorianBruniaux/google-search-console-mcp

Agent Claude Code

Use when writing new tests or improving coverage for gsc-mcp. Knows the pytest fixtures, Google API mocking patterns, and test naming conventions. Examples: "write tests for the new cruxhistory tool", "add edge cases for normalizeurl", "cover sitemapaudit error paths".

Bbeierle12/Skill-MCP-Claude

Agent Claude Code

Periodic health analyst for the Skill-MCP-Claude repo. Audits the skill catalog, reviews skills individually, checks the MCP server contract, verifies docs accuracy, and proposes new skills. READ-ONLY on code — writes a dated Markdown report only. Use for scheduled (cron) repo health passes or on-demand audits.

Diplomat-ai/diplomat-agent

Agent

Reviews Python code for unguarded AI agent tool calls — database writes, API calls, payments, emails, shell commands — that have no validation, rate limiting, or confirmation. Use this when reviewing agent code, after accepting Copilot suggestions, or before committing changes.

chadru/assessor-lookup-public

Agent Claude Code

Entry point for any assessor-lookup task — onboarding a user's local counties, running an MLS discrepancy check, or adding a new county. Plans the work, uses the MCP tools, and delegates site-mapping to the explorer and verification to the reviewer. Start here.

chadru/assessor-lookup-public

Agent Claude Code

Onboards the counties in an appraiser's locale — probes each county's field coverage and configures it for repeated use. Use when a user names the counties they work in (ideally with a sample property each).

chadru/assessor-lookup-public

Agent Claude Code

Maps an unknown county's assessor website to find its data source, API-first. Read-only investigator — returns the endpoints, request shape, and field names a new client would use. Use when adding a county that auto-discovery doesn't already resolve.

mort-lab/excel-mcp

Agent Claude Code

Use proactively to find codebase patterns, coding style and team standards. Specialized agent for deep codebase pattern analysis and convention discovery.

mort-lab/excel-mcp

Agent Claude Code

Use proactivley to research external libraries and fetch relevant documentation for implementation.

skillberry-ai/runspace-agent

Agent Claude Code

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

skillberry-ai/runspace-agent

Agent Claude Code

Compare two outputs WITHOUT knowing which skill produced them.

skillberry-ai/runspace-agent

Agent Claude Code

Evaluate expectations against an execution transcript and outputs.

ruslan-korneev/claude-plugins

Agent

Deep architecture analysis with comprehensive checklist.

ruslan-korneev/claude-plugins

Agent

Analyze dependencies at module, package, and layer levels.

ruslan-korneev/claude-plugins

Agent

Deep interactive feature design for new projects. Use for greenfield projects or major new features.

HaoweiChan/tinboker

Agent Claude Code

Use for auth (Google OAuth, JWT, dev bypass), user profile/watchlist/settings, admin dashboard, dev portal, admin analytics, admin translations, or notifications.

HaoweiChan/tinboker

Agent Claude Code

Use for changes touching the pipelines/ tier — podcast ingestion (Spotify), news ingestion (Tavily/RSS), transcription, summarization, ticker-sentiment extraction, the contentbuilder (LangGraph) pipeline, Marp slides, or the wiki knowledge graph / wikibuilder. Delegate here before grepping pipelines/.

HaoweiChan/tinboker

Agent Claude Code

Use for VPS, Docker, Caddy, Cloudflare, CI/CD workflows, Redis cache, Netdata monitoring, env routing, secrets, or PWA service-worker infrastructure.

cirwel/unitares

Agent

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…

RbBtSn0w/awesome-copilot-mcp

Agent

Python developer agent for testing.

qxbyte/pluginhub

Agent

CODER subagent dispatched by the task-swarm orchestrator. Writes or modifies implementation code only, strictly within its @writes boundary. Never reviews, never scores, never accepts. Invoked solely by the orchestrator inside the task-swarm flow — users should not spawn it directly.

qxbyte/pluginhub

Agent

REVIEWER subagent dispatched by the task-swarm orchestrator (advisory mode). Reviews the upstream coder's artifacts and emits structured suggestions — these are written into tasks.md as > ⚠️ comments for the user to review. Does not participate in the fix loop — the reviewer never fails a stage and never re-dispatches…

qxbyte/pluginhub

Agent

VALIDATOR subagent forked by the task-swarm orchestrator. Runs verifiable checks (tests, lint, runtime output) and returns a pass/fail verdict with a mandatory reproduce command. Has no Edit/Write tool — physically cannot touch code. Invoked only inside the task-swarm flow by the lead orchestrator.

JeonJe/claude-plugins

Agent

Inspects: API contract, cross-project, arch adherence.