tools CLAUDE.md

Project instructions for tools, a multi-module Java library built with Maven, the standard build tool used by many Java projects. It includes code-generation and context-building components for AI agents.

In plain words
What is it for?
Useful when modifying Java modules, Maven plugins, generated protobuf code, context tools, or build and documentation checks.
Why use it?
They identify the authoritative documentation, required Java build practices, and relevant project skills so changes follow the repository’s rules.

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/adamw7/tools/claude-md
Clone the repo
git clone --depth 1 https://github.com/adamw7/tools
Per session 4,697 This file is loaded in full into every session.
When invoked 4,697 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 $0.04697 $0.04697
Opus 5 $0.02348 $0.02348
Sonnet 5 $0.00939 $0.00939
Haiku 4.5 $0.00470 $0.00470

Measured 3d ago against content hash 81b4956f985d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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 · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

AGENTS.md is the single source of truth for agent instructions — repository overview, module layout, build and test commands, CI, environment, and the release process. This file is a quick-reference summary of the essentials; when the two disagree, AGENTS.md wins, and the build's crossDocConsistency enforcer rule fails if a key fact (e.g. the Java version) drifts apart between them.

Detail lives in the thirteen skills under .claude/skills/ (see Agent configuration). Prefer loading the relevant skill over re-deriving a convention.

Project

tools is a multi-module Maven library of Java tooling. Build with Maven 3.9.X: run mvn install from the repository root.

  • Code generation (code/protogen-maven-plugin) — a Maven plugin that generates protobuf builders enforcing missing required fields at compile time (proto2 required, proto3 presence-aware accessors, oneof discriminators). Skill: protogen.
  • Context engineering (code/context) — a regex-based class-usage finder and project-tree builder that assembles context for gen-AI agents, an emitter for Google's Open Knowledge Format (OKF v0.2 bundles of markdown concept documents), plus an MCP server exposing project_tree, find_context, estimate_tokens and okf_bundle. Skill: context-finder.
  • Data (data) — data sources (CSV, GZip, JDBC, Parquet via an in-process DuckDB engine, plus forward-only JSON/YAML/TOON), each in in-memory and iterative variants. Schema-aware sources implement the narrower ColumnarDataSource contract, so a caller needing the schema (e.g. the uniqueness check) cannot be handed a forward-only source. Also a column-uniqueness/key finder, open-addressing collections, and an MCP server exposing the uniqueness checker. Skill: data-sources.
  • Claude Code adoption (adopt) — an ordered pipeline that adopts Claude Code into a GitHub repository: check the toolchain, clone, check the cloned project's own build tool, branch, trust the checkout, claude init and conform the generated CLAUDE.md, wire a build-tool-aware guard in, verify it, push, and open a pull request. The default branch is never written to, clone-URL credentials are masked in everything the run reports and are never left in the checkout's .git/config, --dry-run leaves out the push and the pull request entirely, a git or gh the network refused is tried again with a backoff (--retries) while every other failure is reported at once, and one run adopts a list of repositories without letting a failure stop the rest. Skill: adopt-pipeline.
  • Markdown reading (markdown-common) — the dependency-free reader both the claudeMdFormat rule and adopt's conformer parse a document with, so the checker and the rewriter cannot disagree about what is code, what is commented out, and what heading a line declares. Add no dependency to it.

Read the full file on GitHub · 330 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. 3d ago First seen · 330 lines · 4,697 tokens per session scan A 81b4956f985d

Subscribe to this mod's changes

tools CLAUDE.md is an instructions file published in the GitHub repository adamw7/tools (11 stars, last pushed 5d ago), licensed MIT. It adds 4,697 tokens to every session, about $0.0235 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 2026-08-30.

Related

Other instructions, from other repositories