add CLAUDE.md

add CLAUDE.md is an instructions file for coding agents from MountainUnicorn/add. It costs 817 tokens per session, scanned A, original, MIT.

Development instructions for the ADD (Agent Driven Development) plugin, including its canonical source files, generated runtime files, testing process, and repository layout.

In plain words
What is it for?
Use them when changing ADD features, compiling runtime outputs, testing hooks, checking generated-file drift, or updating project documentation.
Why use it?
They prevent edits to generated files and explain how to rebuild and validate the versions used by Claude and Codex.

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/mountainunicorn/add/claude-md
Clone the repo
git clone --depth 1 https://github.com/MountainUnicorn/add

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 add CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mountainunicorn/add/claude-md.svg)](https://agentmods.dev/instructions/mountainunicorn/add/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mountainunicorn/add/claude-md"><img src="https://agentmods.dev/badge/instructions/mountainunicorn/add/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 817 This file is loaded in full into every session.
When invoked 817 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 $0.00817 $0.00817
Opus 5 $0.00409 $0.00409
Sonnet 5 $0.00163 $0.00163
Haiku 4.5 $0.00082 $0.00082

Measured 4d ago against content hash 2ab65bd74553, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add 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 4d 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADD Development Guide

This repository contains the ADD (Agent Driven Development) plugin source. The marketing site (getadd.dev) lives in a separate repo: MountainUnicorn/getadd.dev.

Source of Truth

core/ is canonical. plugins/add/ (Claude runtime) and dist/codex/ (Codex runtime) are regenerated by scripts/compile.py on every release. Edit core/, never the generated output — the compile-drift CI will reject PRs that disagree.

See runtimes/claude/CLAUDE.md and runtimes/codex/adapter.yaml for runtime-specific concerns.

Project State

  • .add/ — ADD's own project config (dog-fooding itself)
  • docs/ — PRD, milestones, plans, release-signing runbook, codex install guide, infographic
  • specs/ — Feature specifications
  • reports/ — Dashboard snapshots and HTML reports
  • tests/hooks/ — Fixture-based tests for hook scripts

Development Workflow

Test the plugin locally without installing:

claude --plugin-dir ./plugins/add

This loads skills, rules, hooks, knowledge, and templates from the compiled output.

After editing core/:

python3 scripts/compile.py            # regenerate plugins/add/ + dist/codex/
python3 scripts/validate-frontmatter.py
python3 scripts/compile.py --check    # CI parity
bash tests/hooks/test-filter-learnings.sh

Sync to the local marketplace cache so other Claude Code sessions pick up changes:

./scripts/sync-marketplace.sh

Cut a signed release:

./scripts/release.sh vX.Y.Z

Repository Structure

core/                  # Source of truth (runtime-neutral)
  skills/              #   28 skills — all slash commands
  rules/               #   17 auto-loaded behavioral rules (+3 on-demand)
  references/          #   non-autoloaded reference rules (loaded on-demand)
  templates/           #   29 document templates + data manifests
  knowledge/           #   5 Tier-1 knowledge files
  lib/                 #   shared library functions used by hooks/skills
  security/            #   security-related artifacts (threat model, redaction)
  schemas/             #   2 JSON Schema validators
  VERSION              #   Canonical version string

runtimes/claude/       # Claude Code adapter (hooks, plugin manifest, CLAUDE.md)
runtimes/codex/        # Codex CLI adapter

plugins/add/           # GENERATED — Claude Code plugin output
dist/codex/            # GENERATED — Codex CLI prompt + AGENTS.md output

scripts/               # compile.py, sync-marketplace.sh, release.sh, validate-frontmatter.py
docs/                  # Development documentation
specs/                 # Feature specifications
reports/               # Dashboard snapshots
tests/hooks/           # Hook script tests

Read the full file on GitHub · 90 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. 4d ago First seen · 90 lines · 817 tokens per session scan A 2ab65bd74553

Subscribe to this mod's changes

add CLAUDE.md is an instructions file published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 817 tokens to every session, about $0.0041 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