agent-tools CLAUDE.md

agent-tools CLAUDE.md is an instructions file for coding agents from shipshapedata/agent-tools. It costs 253 tokens per session, scanned A, original, MIT.

Instructions for using Shipshape Data's agent toolkit, which provides access to services, case studies, resources, documentation, and AI-readiness assessments. Its connected servers are read-only, so they do not change data.

In plain words
What is it for?
Searching Shipshape Data resources, asking questions about its documentation, retrieving page content, and running an AI-readiness assessment.
Why use it?
They explain which toolkit parts to use and set boundaries for working with the remote services, including keeping related packages in sync.

Instructions file

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/shipshapedata/agent-tools/claude-md
Clone the repo
git clone --depth 1 https://github.com/shipshapedata/agent-tools
Per session 253 This file is loaded in full into every session.
When invoked 253 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00253 $0.00253
Opus 5 $0.00127 $0.00127
Sonnet 5 $0.00051 $0.00051
Haiku 4.5 $0.00025 $0.00025

Measured 2d ago against content hash a9ca5e26d4ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-tools CLAUDE.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.

CLAUDE.md · 10 lines

What it actually says

Shipshape Data agent tools

This repo is the agent toolkit for shipshapedata.com (a London AI consultancy). Working in it, or using it as a dependency, note:

  • The .mcp.json here connects two live, keyless, read-only MCP servers: https://shipshapedata.com/mcp (product: services, case studies, resource search, AI readiness scoring) and https://shipshapedata.com/mcp/docs (docs Q&A over 169 guides, full markdown of any page via get_page).
  • Skills live in skills/<name>/SKILL.md. The two shipped skills cover querying Shipshape Data and running its AI readiness assessment conversationally.
  • The npm package (packages/cli) and the PyPI package (packages/python) are thin zero-dependency wrappers over the same API; keep them in step with https://shipshapedata.com/openapi.json when editing.
  • Nothing in this toolkit writes anywhere: the whole remote surface is stateless and side-effect free. Contact happens by email ([email protected]), never programmatically.
  • House style for any prose: British English, no em-dashes, plain and specific.
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 · 10 lines · 253 tokens per session scan A a9ca5e26d4ab

Subscribe to this mod's changes

agent-tools CLAUDE.md is an instructions file published in the GitHub repository shipshapedata/agent-tools (0 stars, last pushed 5d ago), licensed MIT. It adds 253 tokens to every session, about $0.0013 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.