agentmods.dev

scaffolding-registry

scaffolding-registry is a skill for Claude Code from jamesgray-ai/handsonai-plugins. It costs 155 tokens per session (6,276 once invoked), scanned A, original, MIT.

A setup process for creating an AI Registry: a structured folder of linked notes that records a business’s concepts, workflows, processes, and supporting material.

In plain words
What is it for?
Use it to create the registry structure, document the business schema, write an initial workflow node, and link related business and process information.
Why use it?
It gives an AI workflow a consistent knowledge base instead of leaving business information scattered across files.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

Part of the handsonai plugin — 16 skills shipped together

not rated 8repo changed 4d ago A scan 155 tokens original MIT

Good fit Use it to create the registry structure, document the business schema, write an initial workflow node, and link related business and process information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jamesgray-ai/handsonai-plugins/scaffolding-registry
View source ↗ jamesgray-ai/handsonai-plugins
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 jamesgray-ai/handsonai-plugins --skill scaffolding-registry
Clone the repo
git clone --depth 1 https://github.com/jamesgray-ai/handsonai-plugins

Made for: Claude Code.

Or install handsonai, the plugin that ships this one along with the rest of its 16 skills.

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 scaffolding-registry

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/scaffolding-registry/github.svg)](https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/scaffolding-registry)
Your own site
<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/scaffolding-registry"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/scaffolding-registry/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 scaffolding-registry

Your own site · 80×15
<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/scaffolding-registry"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/scaffolding-registry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,276 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 $0.00155 $0.06276
Opus 5.5 $0.00062 $0.02510
Sonnet 5.5 $0.00031 $0.01255
Haiku 4.5 $0.00015 $0.00628

Measured 4d ago against content hash 68ce43a0e59a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scaffolding-registry 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.

plugins/handsonai/skills/scaffolding-registry/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scaffolding Registry

Stand up a leader's AI Registry as an OKF v0.2 knowledge bundle: a registry/ folder with a SCHEMA.md producer profile and concept nodes for their real business. This is the on-ramp: a guided interview that captures the leader's real business, lines of business, functions, and processes. It names no workflows: the analyze skill does that next, writing them into the backlog.

What this builds

The registry lives in the working folder, the one folder that holds the leader's AI Registry (registry/), their workflows (framework/, the framework folder) and their knowledge graph (knowledge/). Where that folder is depends on where the leader works (see Where the files live below): on Claude Code and Codex it is the workspace; on the web (Claude, ChatGPT) and in Microsoft 365 Copilot (Cowork), a folder in the leader's Google Drive or OneDrive, ai-workspace/ unless they keep another; on Claude desktop, the folder the leader selects in the prompt window. The layout inside it is the same everywhere:

<working folder>/            ← the workspace on Claude Code and Codex; ai-workspace/ (or the leader's own folder) elsewhere
├── REGISTRY.md              ← Tier 1 dashboard (derived, never hand-edited)
├── registry-dashboard.html  ← Tier 2 visual dashboard (derived; always generated at setup)
├── registry/                ← the OKF v0.2 bundle
│   ├── SCHEMA.md            ← producer profile (written by scaffolding-registry)
│   ├── index.md             ← bundle root; frontmatter okf_version: "0.2"
│   ├── log.md               ← setup decisions, schema changes, workflow events
│   ├── businesses/  lines-of-business/  functions/
│   ├── processes/   workflows/          notes/
│   │       (each typed directory has its own index.md)
├── framework/               ← the framework folder (made by the first step that saves a workflow, never by this skill)
│   └── <workflow>/          ← the workflow's record: requirements.md, design-plan.md,
│                              build-record.md, test-results.md, with inputs/, context/
│                              and history/
├── knowledge/               ← the knowledge graph, when the leader builds one (building-knowledge-graph)
├── sops/  process-guides/   ← unchanged homes; nodes link to them

Read the full file on GitHub · 170 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 Changed · +57 lines · -18 tokens per session 68ce43a0e59a
  2. 25d ago Changed 76b0552ee7e4
  3. 26d ago Changed · -3 lines 319b5cdbed2d
  4. 1mo ago Changed · +3 lines c2ff756a7ff2
  5. 1mo ago Changed · +3 lines 71a4e40bb5cb
  6. 1mo ago Changed e14904a78cd0
  7. 1mo ago Changed f472c6c242c9
  8. 1mo ago Changed · -2 lines 33fd572c5d11
  9. 1mo ago Changed · +6 lines · +39 tokens per session 31fd3e21ddd9
  10. 1mo ago First seen · 106 lines · 134 tokens per session scan A 9eed3028ceab

Subscribe to this mod's changes

scaffolding-registry is a skill published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 155 tokens to every session and 6,276 once invoked, about $0.0006 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 2026-08-31.

Building agentsMemory and context
Related

scaffolding-registry compared with skills from other repositories

scaffolding-registry next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
scaffolding-registryjamesgray-ai/handsonai-pluginsSkill8yesterdayMITA155Claude Code
knowledge-ingestopenclaw/openclawSkill394kyesterdayMITA80Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
forgetasgeirtj/system_prompts_leaksSkill71k2d agoCC0-1.0A74Claude Code, Codex
Cortexdanielmiessler/LifeOSSkill20kyesterdayMITA184Claude Code
memoryopensquilla/opensquillaSkill7.1k6d agoApache-2.0A44Claude Code, Codex
ha-data-storesshiwenwen/hope-agentSkill1.9kyesterdayMITA115Claude Code, Codex