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.
npx skills add jamesgray-ai/handsonai-plugins --skill indexing-registrygit clone --depth 1 https://github.com/jamesgray-ai/handsonai-pluginsWrote 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.
[](https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/indexing-registry)<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/indexing-registry"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/indexing-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.
<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/indexing-registry"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/indexing-registry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00129 | $0.01640 |
| Opus 5 | $0.00064 | $0.00820 |
| Sonnet 5 | $0.00026 | $0.00328 |
| Haiku 4.5 | $0.00013 | $0.00164 |
Grade A, and why
indexing-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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintaining the AI Registry
The AI Registry is the registry/ knowledge bundle at the workspace root, plus everything derived from it: directory indexes, GENERATED blocks inside individual nodes, the REGISTRY.md dashboard, and — on request — the visual HTML dashboard.
The registry is derived-state doctrine. The bundle's node files (under registry/) are the source of truth. Every dashboard, index, and summary is generated from them. Edit sources, regenerate — never hand-edit a derived view. If a derived view looks wrong, that's a signal to fix the source node and regenerate, not to patch the view directly.
For how nodes are resolved, written, and owned — resolution rules, write rules, the field-ownership table, framework-progress inference, review scheduling, and the full lint rule list — see references/registry-bundle.md. This skill assumes that contract; it doesn't restate it.
Location & Scope
One workspace = one registry. The bundle lives at registry/ off the root of the folder the framework operates in — beside outputs/, sops/, and process-guides/. Where that root is, and how bytes get read and written there, depends on the platform — see the platform matrix in the framework's cross-platform delivery documentation. Claude Code and Cowork read and write the bundle directly; claude.ai and other connector-based platforms generate and commit through their connector, with anything unwritten stated explicitly.
Terminology: "AI Registry" always means the
registry/bundle and the views generated from it. It is unrelated to the framework's platform registry (registries/platform-registry.json), which catalogs platforms and integrations for the Design and Build skills.
The maintenance pass
Run all five jobs for a full pass, or just the one the user asked for. Other framework skills invoke this skill from their closing step for the same pass — see Best-effort rule below.
1. Lint
Read every node against the workspace's registry/SCHEMA.md and the rule list in references/registry-bundle.md (§6) — that file is the single source; do not duplicate its rule list here. Report findings in plain language, named by file. Offer fixes; never silently repair meaning — a lint pass corrects mechanical issues (formatting, missing index entries) only with the user's confirmation, and never reinterprets or rewrites a node's content on its own judgment.
What ships with it
3 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.
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.
- 10d ago First seen · 97 lines · 129 tokens per session scan A 46c50ec36435
indexing-registry is a skill published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed 29d ago), licensed MIT. It adds 129 tokens to every session and 1,640 once invoked, about $0.0006 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.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.