Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/mercantry/registry/agents-mdgit clone --depth 1 https://github.com/mercantry/registryWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01112 | $0.01112 |
| Opus 5 | $0.00556 | $0.00556 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
registry AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — guide for AI agents in this repository
This file follows the AGENTS.md convention. Two kinds of agents end up here: agents using the registry (you want the MCP tools) and agents working on the codebase (you want the commands and invariants).
If you want to USE the registry
Mercantry is an open commerce registry for AI agents — structured merchant data, honest signals, and real-world booking fulfillment across Los Angeles, Hong Kong, and Tokyo. Read docs/mcp-tools.md — it is written for LLM tool selection, with example transcripts. Summary:
- Connect remotely over Streamable HTTP —
claude mcp add --transport http mercantry https://mercantry.org/mcp— or locally over stdio (npm run mcp). Both transports serve the identical tool surface. A REST mirror lives at/v1(OpenAPI at/v1/openapi.json; self-serve keys:POST /v1/keyswithdeveloper_name+contact; bulk export:GET /v1/export/merchants.ndjson— bulk ingestion, caching, and training on the data are permitted per the open license). - Fulfillment is human-operated (voice automation is deferred): real bookings are accepted only for phone-verified
bookablemerchants and are worked during 12:00–23:00 Asia/Shanghai (04:00–15:00 UTC), with an honest queue + 24h auto-fail.sandbox: truemerchants give deterministic test outcomes and never touch a real restaurant. Checkget_registry_metafor current coverage and verification counts before assuming anything. - Read tools:
search_merchants(filter-based, never ranked, deterministic order),get_merchant(full signal dump),get_availability(honest: checks happen at booking time),get_registry_meta(evaluate the registry itself, staleness included). - Booking is async:
place_booking→ pollget_booking_statusor passcallback_url. Setaccept_within_window: trueso merchant counter-offers inside your window confirm without a round-trip. - Always
cancel_bookingwhen plans change. No-shows are tracked per developer key; high no-show keys get throttled. submit_feedbackonly after a confirmed booking, once, within 14 days.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 59 lines · 1,112 tokens per session scan A 96b0cb9e236a
registry AGENTS.md is an instructions file published in the GitHub repository mercantry/registry (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,112 tokens to every session, about $0.0056 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.