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 agentmods add instructions/richardofortune/cadloop/claude-mdgit clone --depth 1 https://github.com/richardofortune/cadloopWrote 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/instructions/richardofortune/cadloop/claude-md)<a href="https://agentmods.dev/instructions/richardofortune/cadloop/claude-md"><img src="https://agentmods.dev/badge/instructions/richardofortune/cadloop/claude-md.svg" alt="Measured on agentmods" 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 | $0.00327 | $0.00327 |
| Opus 5 | $0.00163 | $0.00163 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
cadloop 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 3d 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.
What it actually says
cadloop — notes for agents
Review loop (Tyrekick)
docs/walkthrough/pen-holes/index.html carries a Tyrekick widget, so reviewers
can pin comments on the page and an agent can read them back here.
| project slug | cadloop-pen-holes |
| review URL | https://cadloop-pen-holes.pages.dev (Cloudflare Pages project cadloop-pen-holes) |
| destination | https://tyrekick-cadloop-pen-holes.richard-fortune.workers.dev |
| transport | json (Cloudflare Worker, no Discord mirror) |
| worker | tyrekick-cadloop-pen-holes, source in tools/tyrekick-worker/ |
| KV namespace | cadloop-pen-holes-FEEDBACK |
| management token | Cloudflare secret TYREKICK_TOKEN on that worker — never in this repo |
The read-back is registered as the tyrekick MCP server for this project, so
"list the open feedback and fix what people flagged" works in any session here.
Re-deploying the page after an edit:
npx wrangler pages deploy docs/walkthrough/pen-holes \
--project-name cadloop-pen-holes --branch main
Do not point this page at a different destination. If another part of the repo needs reviewing, give it its own slug and its own worker rather than sharing this store.
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.
- 3d ago First seen · 31 lines · 327 tokens per session scan A b8acbbcdf17e
cadloop CLAUDE.md is an instructions file published in the GitHub repository richardofortune/cadloop (1 stars, last pushed 1mo ago), licensed MIT. It adds 327 tokens to every session, about $0.0016 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 instructions, from other repositories
CADCLAW AGENTS.md
AGENTS.md instructions for sunnyday-technologies/CADCLAW, covering agents.md — guidance for ai assistants using cadclaw, what cadclaw is, and what it is not, the core rule: place authored parts, don't generate them, why this rule exists and what you may generate.
kernelCAD-web CLAUDE.md
Instructions for w1ne/kernelCAD-web, covering deployment, cad authoring discipline and demo discipline (v0.x.0-tag pr review rule).
nurb CLAUDE.md
Claude Code instructions for Shpigford/nurb, covering nurb, delegation policy (read first), the part contract, commands and layout.
openscad-studio AGENTS.md
AGENTS.md instructions for zacharyfmarion/openscad-studio, covering agents.md - ai agent architecture, design context, users, brand personality and aesthetic direction.
nurb AGENTS.md
AGENTS.md instructions for Shpigford/nurb, a project described as: Agentic CAD for 3D printing.
printyourduck-mcp AGENTS.md
AGENTS.md instructions for printyourduck/printyourduck-mcp, covering agent guide, product boundary, commands, repo ownership and release truth.