agentmods.dev

ai-dev-toolkit: Instructions file for Claude Code

CLAUDE.md

ai-dev-toolkit CLAUDE.md is an instructions file for Claude Code from saketananddotme/ai-dev-toolkit. It costs 388 tokens per session, scanned A, original, MIT.

Project instructions for ai-dev-toolkit, a command-line package manager for AI skills, agents, rules and hooks. It installs sources from Git repositories and links them into tools such as Cursor, Claude Code and Codex.

In plain words
What is it for?
Use them when working on source installation, symlinks, harness detection, project scope, catalogue entries or the adt command set.
Why use it?
They explain the difference between installing a source and making it available to an AI coding tool, including global and project-specific use.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

This is saketananddotme/ai-dev-toolkit's own configuration. It tells Claude Code how to work on ai-dev-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-dev-toolkit configures →

not rated 12repo +3 4mo ago A scan 388 tokens original MIT
View source ↗ saketananddotme/ai-dev-toolkit
Reuse

Borrowing it

Nothing to install: this file belongs to saketananddotme/ai-dev-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/saketananddotme/ai-dev-toolkit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/saketananddotme/ai-dev-toolkit

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 ai-dev-toolkit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/saketananddotme/ai-dev-toolkit/claude-md/github.svg)](https://agentmods.dev/instructions/saketananddotme/ai-dev-toolkit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/saketananddotme/ai-dev-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/saketananddotme/ai-dev-toolkit/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-dev-toolkit CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/saketananddotme/ai-dev-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/saketananddotme/ai-dev-toolkit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 388 This file is loaded in full into every session.
When invoked 388 The same file — it is already loaded in full.
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 $0.00388 $0.00388
Opus 5.5 $0.00155 $0.00155
Sonnet 5.5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 2mo ago against content hash 3a536c01ca75, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-dev-toolkit 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 2mo 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 · 40 lines

What it actually says

ai-dev-toolkit (adt)

A CLI package manager for AI skills, agents, rules, and hooks across Cursor, Claude Code, and Codex.

What it does

adt is a zero-dependency Node.js CLI (bin/adt.js) that lets users install skill sources (git repos) and symlink them into harness directories — globally (~/.claude/, ~/.cursor/) or per-project (.claude/, .cursor/).

Key concepts

  • Source — a git repo containing skills/agents/rules/hooks (e.g. obra, karpathy)
  • Install — clones a source to ~/.adt/sources/; nothing is wired yet
  • Use — creates symlinks from the source into harness dirs; scope-aware (global vs project)
  • Scope — project if inside a .git repo or a dir with .adt; global otherwise

File layout

bin/adt.js     — entire CLI (~1400 lines, single file, no deps)
catalog.json   — built-in catalog of known sources

Commands

adt init                  — detect harnesses, write ~/.adt/ structure
adt install <source>      — clone source to ~/.adt/sources/
adt use [--global] [src]  — symlink source into harness dirs
adt uninstall             — remove symlinks and cleanup
adt list                  — show installed sources
adt search                — search the catalog

Conventions

  • No external runtime dependencies — stdlib only
  • All state in ~/.adt/ (manifest, state, remote catalog cache)
  • Harness paths are defined in globalHarnessDirs() and projectHarnessDirs() at the top of bin/adt.js
  • Catalog TTL: 24 hours for remote refresh
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. 2mo ago First seen · 40 lines · 388 tokens per session scan A 3a536c01ca75

Subscribe to this mod's changes

ai-dev-toolkit CLAUDE.md is an instructions file published in the GitHub repository saketananddotme/ai-dev-toolkit (12 stars, last pushed 4mo ago), licensed MIT. It adds 388 tokens to every session, about $0.0016 per session on Opus 5.5. 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.

Building agents
Related

ai-dev-toolkit CLAUDE.md compared with instructions from other repositories

ai-dev-toolkit CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ai-dev-toolkit CLAUDE.mdsaketananddotme/ai-dev-toolkitInstructions file124mo agoMITA388Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode