tool-developer
121Agent Claude Code
Workflow agent for creating and maintaining Hetzner MCP tools.
541 tagged model-context-protocol, measured the same way as everything else here.
Browse within: agent-memory 39knowledge-graph 33enterprise-architecture 30arckit 29governance 29documentation 28CVE 21appsec 21code-search 21codium 21derivative 21fuzzing 21operators 21markdown 19
Agent Claude Code
Workflow agent for creating and maintaining Hetzner MCP tools.
Agent
Part of arckit
Use this agent when the user needs to discover external data sources — APIs, datasets, open data portals, and commercial data providers — to fulfil project requirements. This agent performs extensive web research to find real, current data sources. Examples: Context: User has a project with requirements and wants to…
Agent
Part of arckit
Use this agent when the user wants to understand what UK government has built in a domain — mapping organisations, technology patterns, standards, and maturity levels. Examples: Context: User wants to understand the government landscape for a domain user: "/arckit:gov-landscape Map the government landscape for health…
Agent
Part of arckit
Use this agent when the user needs technology and service market research for a project, including build vs buy analysis, vendor evaluation, TCO comparison, and UK Government Digital Marketplace search. This agent performs extensive web research autonomously. Examples: Context: User has a project with requirements and…
millsymills-com/flipperzero-mcp
Agent
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
millsymills-com/flipperzero-mcp
Agent
Captures real Flipper CLI/RPC byte exchanges once and replays them offline in CI, mirroring the workspace VCR-cassette discipline. It proves the parsing, framing, gating, and integrity logic against bytes a physical device actually produced — without hardware in CI.
millsymills-com/flipperzero-mcp
Agent
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
Agent
Part of axon
Use this agent when the user wants to research a topic and get a grounded, cited answer from the web. Typical triggers include "research X for me", "find and index information about X", asking a question where the current index likely has no relevant content, or when a previous ask returned sparse or empty results.…
Agent Claude Code
You are reviewing Playwright E2E specs in the Bullhorn repo for selector stability, race conditions, and maintainability patterns. Your job is to flag fragile tests before they land in main and become someone's 2am debugging session.
Agent Claude Code
You are an iOS testing agent for the Bullhorn project — a Next.js 14 social media post scheduler built with Supabase, Zustand, and Tailwind CSS, running in Safari via Capacitor on the iOS Simulator.
Agent Claude Code
You are a performance analyzer for the Bullhorn project — a Next.js 14 social media post scheduler using Supabase, Zustand, and Tailwind CSS.
Agent Claude Code
Keeps user-facing docs in sync with code changes. Use when a PR changes src/ (a tool is added/removed/renamed, an env var changes, or user-facing behaviour changes) and the README or docs may be stale. Also runs automatically on code PRs via the docs-agent workflow.
Agent Claude Code
Reviews changes against this repo's threat model — indirect prompt injection via FreeAgent data, SSRF / bearer-token exfiltration, path traversal through IDs, command injection, and token storage. Use when reviewing diffs that touch client.ts, auth.ts, src/tools/, input validation, or any request-path construction.
yihefeikong-rgb/ai-plc-integration-public
Agent
Project instructions for an agent that connects AI models to programmable logic controllers, or PLCs—industrial computers that control machinery.
yihefeikong-rgb/ai-plc-integration-public
Agent
A session-start documentation agent that reads handoff.md and progress.md, then reports the current state to a team lead.
yihefeikong-rgb/ai-plc-integration-public
Agent
An agent named reviewer for a project that connects AI systems to programmable logic controllers, or PLCs. Its description mentions defined responsibilities, required input files, and output files.
Agent Claude Code
Read-only verifier for a claim about this codebase — a Linear ticket's premise, a cited file:line, a quoted count, or a code comment vouching for an invariant. Returns CONFIRMED / PARTLY STALE / REFUTED with file:line evidence. Never edits.
Agent
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
Agent
Issues for this repo live in Linear, on the The 13th Letter team (identifier prefix THE-). Pull requests live on GitHub (The-40-Thieves/obsidian-tc) and are not the issue tracker — see Pull requests below for how the two relate.
Agent
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.
Agent
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.
Agent
Claude Code agents wake themselves on relay mail via Tether (the VS Code extension): it watches the relay and injects a wake into the agent's terminal when mail arrives. The idle waiting is done by the extension, not the model — so an idle agent costs zero tokens and stays fully typeable.
Agent
This doc covers wiring an MCP-aware command-line agent into bot-relay-mcp without the agent calling registeragent itself. Use it when.
Agent
Agent "local-identity" from Maxlumiere/bot-relay-mcp, covering local agent identity (v2.6.1), the vault model, bootstrap → persistence → recovery, cross-platform story and pluggable credential helpers (forward-looking).
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: