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 | $0.02945 |
| Opus 5.5 | $0.00052 | $0.01178 |
| Sonnet 5.5 | $0.00026 | $0.00589 |
| Haiku 4.5 | $0.00013 | $0.00295 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 102 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 plus everything derived from it: directory indexes, GENERATED blocks inside individual nodes, the REGISTRY.md dashboard, and the visual HTML dashboard (always generated at the end of registry setup; once it exists, refreshed on every pass).
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, fix the source node and regenerate; never patch the view.
For where the bundle is and how nodes are written and owned (resolution, write rules, the field-ownership table, the registry log, how progress and the re-check date are shown, and the full lint rule list), see references/registry-bundle.md. This skill assumes that contract; it doesn't restate it. A workflow's progress is never stored: it is read from the workflow's folder by the routing rule, through the framework-state script where code can run (references/tier-2-island.md has the by-hand reading). Its re-check date is Test's stale_after.
Location & Scope
One working folder = one registry. On Claude Code and Codex the bundle is registry/ in the workspace, beside framework/, sops/ and process-guides/. On Claude desktop it is registry/ inside the working folder the leader selected, beside framework/. On the web (Claude, ChatGPT) and in Microsoft 365 Copilot it is registry/ in the working folder (ai-workspace/, or the leader's own folder) in their Google Drive or OneDrive, read and written through the platform's connection, by the drive-saving rule in references/registry-bundle.md. REGISTRY.md and registry-dashboard.html sit beside registry/, in its parent folder. Only where there are no files and no drive connection that can write does the skill fall back to print-to-save: it gives each file complete with its location for the leader to save, and says plainly what is unsaved. The skill never assumes a Git repository.
What ships with it
4 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.
- 4d ago Changed · +6 lines b92f13d4cb11
- 26d ago Changed 0290c516c28e
- 1mo ago Changed 0c69fda03ee6
- 1mo ago Changed · -1 lines 3e8c6982dcea
- 1mo ago Changed d8fd546f82c4
- 2mo 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 yesterday), licensed MIT. It adds 129 tokens to every session and 2,945 once invoked, about $0.0005 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.
indexing-registry compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| indexing-registryjamesgray-ai/handsonai-plugins | Skill | 8 | yesterday | MIT | A | 129 | Claude Code |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 74 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |