The real catalog of tools for AI agents

Signed, versioned ledger of standing instructions with intake contradiction diffs.

California Jury Instructions — CACI (civil) and CALCRIM (criminal), official text as adopted by…

Dockerfile instruction count, body discarded

Standing minted only from signed settlement receipts, never reviews. Verdicts: ACCEPT to DECLINE.

Search and retrieve agent instruction files: system prompts, skills, workflows, and safety filters.

Test whether AI agents retain critical instructions as conversations grow.

Memory for coding conventions and standing instructions that persists across sessions.

Shared, cited knowledge-graph memory for agents — ask, search, remember, keep standing instructions

Create guides as MCP servers to instruct coding agents to use your software (library, API, etc).

Discover flat-rate DeepSeek plans, model limits, API-key instructions, and coding-client setup.

Research honeypot. Logs connections and tool arguments; injects instructions. Read README first.

Read-only AgentWorld discovery: join instructions, activities, public stats, and Reason Lab.

Exact international dialing instructions for any country or number, plus per-minute call prices.

Reuse your team's AI instructions (Bindings and Stacks) from Bindry in any MCP client.

Read-only MCP server for the WebAssembly spec: instructions, types, sections, search, proposals.

Scan any public URL for hidden instructions aimed at AI agents (prompt injection). Free, no auth.

Operating contracts for AI agents. Structured instructions compiled into system prompts.

Create Markdown instructions for AI agents to build, deploy, and maintain an Astro website.

Score text and web pages for signs of AI writing; check images for hidden AI instructions.

Just-in-time instructions for agents: upload docs, serve only the sections each turn needs.