Categories › AI & Agents › Multi-agent, orchestration & workflows
Small tools for agent builders: AI-writing tells, tools/list token cost, CLAUDE.md lint, and more.
Remote server: your requests and data go to toolbox.allthepossibles.com. Claude Code: claude mcp add --transport http toolbox https://toolbox.allthepossibles.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
check_tells — Check text for AI-writing tells (em-dashes, 'not just X but Y', rule-of-three lists, stock vocabulary like delve or seamlessly, hedge words,manifest_cost — Estimate what an MCP server's tools/list costs in tokens on every session start, per tool, with the three most expensive tools and flags forlint_agent_md — Lint a CLAUDE.md, AGENTS.md or MEMORY.md: line count against Claude Code's 200-line memory index cap, estimated tokens, duplicate lines, conmcp_install_snippets — Generate install snippets for an MCP endpoint (Claude Code, Claude Desktop, Cursor, Codex, VS Code, curl) and probe the endpoint once to concheck_ai_crawlers — Read a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are alcheck_headers — Fetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permcheck_page_meta — Fetch a URL and report what crawlers and link unfurlers see: title and meta description with lengths, canonical, lang, viewport, robots metajson_to_schema — Turn a JSON sample (or an array of samples of the same shape) into a JSON Schema draft 2020-12 and a TypeScript type. Infers required vs optexplain_cron — Explain a five-field cron expression in plain English, list the next runs in UTC, and warn about the cases Cloudflare Workers, GitHub Actionscrub_env — Scrub a .env file into a safe .env.example: every value is blanked or replaced with a placeholder that keeps its shape (postgres://USER:PASStrace_redirects — Trace a URL's redirect chain hop by hop (up to 10 hops, 8 s each) with status, location, timing and scheme per hop. Flags chains over two recheck_sitemap — Check a site's sitemaps: discovers them from robots.txt, /sitemap.xml and /sitemap_index.xml, reads index files one level deep (20 children decode_jwt — Decode a JWT's header and payload without verifying the signature (it never takes a secret). Returns the claims with iat, nbf and exp as ISOlint_mcp_tools — Lint the tools an MCP server lists, from the model's side of the wire: names that break Claude's ^[a-zA-Z0-9_-]{1,64}$ rule, duplicate namesNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.