agentmods.dev

agent-tools AGENTS.md

A repository guide for AI coding agents working on the Ada Diamonds plugin, a package that connects agents to Ada Diamonds' services.

In plain words
What is it for?
Use it when editing the plugin, working with its shopping, API, MCP connection, or checkout instructions, or validating changes before committing.
Why use it?
It explains the repository's files, available skills, service connections, and validation rules so agents can make appropriate changes.

Instructions file for CodexOpenCode

2 5d ago B scan 1,026 tokens original MIT
View the source file adadiamonds/agent-tools
Install

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.

agentmods
npx agentmods add instructions/adadiamonds/agent-tools/agents-md
Clone the repo
git clone --depth 1 https://github.com/adadiamonds/agent-tools

Made for: Codex, OpenCode.

Per session 1,026 This file is loaded in full into every session.
When invoked 1,026 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.01026 $0.01026
Opus 5 $0.00513 $0.00513
Sonnet 5 $0.00205 $0.00205
Haiku 4.5 $0.00103 $0.00103

Measured 2d ago against content hash 457e4dc0e18f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

agent-tools AGENTS.md scanned grade B with 1 finding 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

- `mcp.json` servers must have `type` and an absolute `https` `url` (for `streamable-http` / `sse`); no secrets in headers.
AGENTS.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents working in this repository.

What this repository is

adadiamonds/agent-tools is the official, public Ada Diamonds plugin for AI agents. It contains no application code. It is:

  • plugin.json: an Agent Plugins 1.0.0 manifest.
  • mcp.json: the two Ada Diamonds MCP servers (ada-diamonds at https://www.adadiamonds.com/mcp, ada-diamonds-docs at https://www.adadiamonds.com/mcp/docs), Streamable HTTP, anonymous.
  • skills/<name>/SKILL.md: four Agent Skills:
    • ada-diamonds-shopping: search the catalog and quote a complete ring (setting plus loose diamond, USD).
    • ada-diamonds-api: the public REST API reference (endpoints, auth, scopes, sandbox key, rate limits, errors, versioning).
    • ada-diamonds-mcp: connecting to and using the MCP servers from Claude Code, Claude Desktop, Cursor, ChatGPT, or any client.
    • ada-diamonds-commerce: agentic checkout (ACP checkout sessions, product feed, UCP discovery, sandbox vs live, webhooks).
  • scripts/validate.mjs: the test suite. Plain Node, no dependencies.

The live source of truth for every fact in the skills is https://www.adadiamonds.com/developers (also served as markdown with Accept: text/markdown), https://www.adadiamonds.com/openapi.json, and https://www.adadiamonds.com/agents.md. When a skill and the live docs disagree, the live docs win; fix the skill.

How to use the skills here

Consumers install them with npx skills add adadiamonds/agent-tools (see README). Inside this repo, when you are asked a question about Ada Diamonds' API or checkout, read the relevant SKILL.md before answering; do not answer from memory.

Editing rules

  • Keep every fact consistent with the live docs above. Do not invent endpoints, parameters, scopes, or prices.
  • Prices in every example are US dollars as decimals, never cents.
  • An engagement ring is a setting plus a loose diamond, priced separately. Every example that quotes a ring must show both numbers and the sum.
  • Frontmatter: name must equal the directory name; description non-empty and at most 1024 characters, written as "what it does and when to use it"; keep license: MIT and metadata.homepage. Single-line values only (no YAML block scalars).
  • Keep each SKILL.md under 500 lines. Long tables go in references/ inside the same skill directory and are linked relatively.
  • Only the keys allowed by the Agent Plugins closed schema may appear in plugin.json ($schema, name, version, description, author, homepage, repository, license, keywords, extensions). Skills and MCP servers are never declared inline in plugin.json.
  • mcp.json servers must have type and an absolute https url (for streamable-http / sse); no secrets in headers.
  • Prose style: no em dashes; use commas, periods, or parentheses.
  • Bump version in plugin.json and add a line to CHANGELOG.md for any user-visible change.

Read the full file on GitHub · 55 lines

Changes

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.

  1. 2d ago First seen · 55 lines · 1,026 tokens per session scan B 457e4dc0e18f

Subscribe to this mod's changes

agent-tools AGENTS.md is an instructions file published in the GitHub repository adadiamonds/agent-tools (2 stars, last pushed 5d ago), licensed MIT. It adds 1,026 tokens to every session, about $0.0051 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

agent-pluginsagent-skillsai-agentslab-grown-diamondsmcpmcp-server
Related

Other instructions, from other repositories

intervals-icu-mcp CLAUDE.md

Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.

hhopke/intervals-icu-mcp · 2,035 tokens

ai-toolkit AGENTS.md

Instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).

pipefy/ai-toolkit · 3,184 tokens

flyto-core CLAUDE.md

Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.

flytohub/flyto-core · 367 tokens

Plonk AGENTS.md

Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.

ostapondo/Plonk · 3,557 tokens

rosetta AGENTS.md

Instructions for tikoci/rosetta, covering codex instructions for rosetta, first reads, development defaults and mcp and client config.

tikoci/rosetta · 595 tokens

pharo-smalltalk-interop-mcp-server CLAUDE.md

Instructions for mumez/pharo-smalltalk-interop-mcp-server, covering claude.md, project overview, development setup, environment variables and common commands.

mumez/pharo-smalltalk-interop-mcp-server · 2,406 tokens