tool-spec

tool-spec is a skill for Claude Code from MangroveTechnologies/mangrove-agent. It costs 99 tokens per session (1,044 once invoked), scanned A, original, MIT.

A specification-writing tool for designing a new MCP tool for the mangrove-agent service. An MCP tool is a defined action an AI agent can call, including its inputs, access rules, and description.

In plain words
What is it for?
Use it to define a tool name, JSON-shaped inputs, access tier, description, safeguards, and the service-layer behavior needed for a new extension.
Why use it?
It turns a requested capability into a format that matches the application's existing tool and service conventions. This reduces ambiguity before implementation.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions CLAUDE.md.

Good fit Use it to define a tool name, JSON-shaped inputs, access tier, description, safeguards, and the service-layer behavior needed for a new extension.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mangrovetechnologies/mangrove-agent/tool-spec
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.

Any agent
npx skills add MangroveTechnologies/mangrove-agent --skill tool-spec
Clone the repo
git clone --depth 1 https://github.com/MangroveTechnologies/mangrove-agent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tool-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/mangrovetechnologies/mangrove-agent/tool-spec.svg)](https://agentmods.dev/skills/mangrovetechnologies/mangrove-agent/tool-spec)
Your own site
<a href="https://agentmods.dev/skills/mangrovetechnologies/mangrove-agent/tool-spec"><img src="https://agentmods.dev/badge/skills/mangrovetechnologies/mangrove-agent/tool-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,044 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00099 $0.01044
Opus 5 $0.00049 $0.00522
Sonnet 5 $0.00020 $0.00209
Haiku 4.5 $0.00010 $0.00104

Measured 7d ago against content hash c1a6cfb020d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tool-spec 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 7d 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.

.claude/skills/tool-spec/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Draft MCP Tool Specification

Parse $ARGUMENTS as a natural-language description of the tool you want to add (no project prefix — this skill is scoped to mangrove-agent).

Produce a complete MCP tool specification following the conventions already in server/src/mcp/tools.py and the service-layer pattern documented in docs/contributing.md and CLAUDE.md.

Output sections

1. Tool name

Lowercase snake_case. No prefix (the MCP server is single-tenant; all tools live under mcp__mangrove-agent__*). Match existing patterns: get_balances, create_strategy_autonomous, list_trades, evaluate_strategy.

2. Access tier

Pick one:

  • free — no API key required. Reserve for status, list_tools, read-only discovery endpoints that can't leak wallet/strategy data.
  • auth — requires api_key param matching API_KEYS in config. Default tier for everything else.
  • x402 — payment-gated via the x402 protocol. Currently demo-only (hello_mangrove). Add this tier only on explicit product decision.

3. Description

One sentence. Match the tone of existing tool descriptions — direct, imperative, and it should state any guard or precondition ("Requires backup-confirmed wallet", "Paper mode only", etc.).

4. Parameters

For each parameter give: name, type, required, description. Standard patterns:

  • api_key: str = "" is always last in the param list and required when access != free.
  • Addresses use str with the natural 0x-prefixed hex convention; chain_id uses int.
  • Slippage / fee params are float in decimal form (0.002 = 0.2%), with the cap in the description.
  • Token params accept either symbol or contract address (document which is preferred for the route).

5. Service-layer function

Every MCP tool calls into a function in server/src/services/<resource>.py. Give the function signature the tool will call — the service layer owns the business logic, the tool layer only authenticates + marshals.

6. Response shape

JSON dict with explicit keys. Never return raw model objects without .model_dump(mode="json"). Never return encrypted secrets, Fernet ciphertext, or plaintext key material (the signing guard blocks that at the wallet layer, but your tool should not be a bypass).

Read the full file on GitHub · 72 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. 7d ago First seen · 72 lines · 99 tokens per session scan A c1a6cfb020d8

Subscribe to this mod's changes

tool-spec is a skill published in the GitHub repository MangroveTechnologies/mangrove-agent (5 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 1,044 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

sui-publish

Publishing, upgrading, and deploying Sui Move packages. Use this skill when the user needs to publish a package, upgrade a published package, deploy to multiple networks, serialize transactions for multisig signing, run a local Sui network (localnet), prepare for Mainnet launch, monitor production deployments, or…

mission69b/t2000 · 133 tokens

t2000-job

Escrow USDC for agent-to-agent deliverable work (A2A jobs). Use when hiring another agent for async work (research reports, builds, SLA tasks) or when selling deliverable work yourself (list a service: fixed price + SLA, no server needed), or posting/claiming open jobs on the board (t2 job open / claim) — anything…

mission69b/t2000 · 164 tokens

t2000-engineering

The deep version of the t2000 engineering discipline — trace-the-full-path debugging, verifiable success criteria, simplicity/surgical-change rules, complete-removal (no orphans), and the Musk product algorithm. CLAUDE.md carries the one-line assertions; read this for the worked examples, the ask-vs-proceed test, the…

mission69b/t2000 · 137 tokens

t2000-setup

Set up a t2000 terminal Agent Wallet (t2 init) when the user needs a local CLI key file — not for Claude-only marketplace (that is Passport Connect OAuth only). Also use when they say "set up t2000", "install the wallet", or "connect t2000 to Claude / Cursor" if a local wallet is in scope. Covers npm CLI install…

mission69b/t2000 · 113 tokens

move-unit-testing

Use when writing unit tests for Move smart contracts on Sui. Applies to test function naming, assertions, test attributes, context usage, and cleanup patterns. Use whenever user asks to write tests, add tests, or test a Move module.

mission69b/t2000 · 52 tokens

sui-object-model

Deep reference for the Sui object model: ownership types, object abilities, dynamic fields, collections, versioning, transfer patterns, and derived objects. Use this skill whenever the user asks about Sui objects, object ownership (address-owned, shared, immutable, wrapped), how to transfer or share or freeze objects…

mission69b/t2000 · 152 tokens