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.
git clone --depth 1 https://github.com/SecondLifes/delphi-expertWrote 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/rules/secondlifes/delphi-expert/local-machine-registry)<a href="https://agentmods.dev/rules/secondlifes/delphi-expert/local-machine-registry"><img src="https://agentmods.dev/badge/rules/secondlifes/delphi-expert/local-machine-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/rules/secondlifes/delphi-expert/local-machine-registry"><img src="https://agentmods.dev/badge/rules/secondlifes/delphi-expert/local-machine-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 | $0.02135 | $0.02135 |
| Opus 5.5 | $0.00854 | $0.00854 |
| Sonnet 5.5 | $0.00427 | $0.00427 |
| Haiku 4.5 | $0.00214 | $0.00214 |
Grade C, and why
local-machine-registry scanned grade C with 1 finding 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
1. **Never `rm -rf` anything under the hub root.** Removing links is Copies of this mod
1 near-identical copy found in the catalogue:
- local-machine-registry — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The .rad Hub — Single Machine-Wide Root, One JSON File, Live Reference
One root, %ProgramData%\rad (Windows) / /usr/local/share/rad. Outside
every repo, never committed, never published. Holds a single
settings.json, skills\ (the categorized link farm), and a handful of
convenience links (rad.ps1, workspace, tools, rules, prompts,
analysis, spec-kits\) — every one of them a live link, never a
copy, into the registered workspace's own files. Nothing under the hub
root is a primary source; the workspace is.
One JSON file, not two. An earlier design split machine-wide facts
(which workspace, which kits) and personal settings into
registry.json + settings.json. There was no real reason for the
split — settings.json alone now holds both.
Live reference, not publish-and-copy. rules\, prompts\ and
analysis\ under the hub root are not populated by copying files — they
are single links straight into the workspace's own share\rules\,
share\prompts\ and share\analysis\. Reading through the hub link and
reading the workspace's share\ folder directly are the same files. If
the workspace's real path is ever unreachable, the correct response is
"workspace unreachable, cannot resolve" — never a guess and never a
silently stale fallback copy from some earlier "publish" step, because
there is no publish step anymore.
Built and maintained by tools/rad.ps1 in the AI-Spec-Kits-Maker
workspace. Idempotent, needs no elevation.
A missing hub root is never fatal. It means cross-kit references and
shared rules are unavailable on this machine — say so plainly and point at
pwsh tools/rad.ps1 -Action Install; never guess the content that would
have been there.
settings.json — the shared source of truth
{
"schema_version": 3,
"updated": "2026-07-31 08:16",
"updated_by": "user@MACHINE",
"root": "E:\\...\\AI-Spec-Kits-Maker",
"last_bootstrap": { "date": "...", "machine": "..." },
"kits": {
"erp-muhasebe-temel": {
"path": "E:\\...\\spec-kits\\erp-muhasebe-temel",
"registered_at": "...", "registered_by": "...", "machine": "..."
}
}
}
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.
- 1mo ago First seen · 184 lines · 2,135 tokens per session scan C 4b619574ed19
local-machine-registry is a cursor rule published in the GitHub repository SecondLifes/delphi-expert (3 stars, last pushed 1mo ago), licensed MIT. It adds 2,135 tokens to every session, about $0.0085 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other cursor rules, from other repositories
slice-tasks
PLANNING SPINE STEP 2 of 3 — Slice the work: break a scoped PRD into vertical-slice stories in specs/epics/. Use after scope-work (step 1), before plan-work (step 3). Not a substitute for scope-work or plan-work.
iris
GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after review. Never pushes or merges without explicit human approval. Integrates with VS Code GitHub Pull Requests extension.
elite-orchestrator
Elite orchestrator for mission-critical, enterprise-scale tasks requiring strategic coordination of 7+ agents across all domains. Makes architectural decisions, manages risk, ensures business continuity, and delivers enterprise-grade outcomes. Use for platform migrations, security incidents, multi-system integrations…
project-onboarding-rule
Automatically onboards existing projects into the AI-driven development workflow.
linear-in-review
After finishing a Linear issue, set its status to In Review (never Done).
sprint-planning
BMAD BMM Agent: sprint-planning.