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/jmenzies722/shua-labsWrote 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/jmenzies722/shua-labs/hard-constraints)<a href="https://agentmods.dev/rules/jmenzies722/shua-labs/hard-constraints"><img src="https://agentmods.dev/badge/rules/jmenzies722/shua-labs/hard-constraints/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/jmenzies722/shua-labs/hard-constraints"><img src="https://agentmods.dev/badge/rules/jmenzies722/shua-labs/hard-constraints.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 | $0.00115 | $0.00115 |
| Opus 5 | $0.00057 | $0.00057 |
| Sonnet 5 | $0.00023 | $0.00023 |
| Haiku 4.5 | $0.00012 | $0.00012 |
Grade A, and why
hard-constraints 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.
What it actually says
- Public site tells the truth: founding lab, no invented traction.
- Do not invent customers, revenue, follower counts, or live social URLs.
- Do not leak private
company-osinternals. - Do not impersonate the founder.
- Do not create Instagram/YouTube accounts or publish posts from this repo.
- Social stays
live: falseindata/site.tsuntil the founder opens the channel. - Content edits belong in
data/site.ts.
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 · 13 lines · 115 tokens per session scan A 391e476a598f
hard-constraints is a cursor rule published in the GitHub repository jmenzies722/shua-labs (2 stars, last pushed 6d ago), licensed MIT. It adds 115 tokens to every session, 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 cursor rules, from other repositories
goal-flight
Goal Flight controller rules.
specify-rules
For additional context about technologies to be used, project structure, shell commands, and other important information, read the current plan: specs/001-react-profiler-mcp-bridge/plan.md (and linked research.md, data-model.md, contracts/, quickstart.md in that directory).
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
codex-premium-website-skills
Apply Codex Skills standards to frontend, website, motion, accessibility, QA, agent reasoning, and handoff work.
hatch3r-dynamic-stack-verification
Runtime-evidence gates for stacks with no static type layer (plain-JS Vue, dynamic persistence) — smoke-mount changed components, dormant-collection-read ratchet, runtime smoke evidence on module-boundary changes; a green lint+build+mock-suite proves a layer, not the system.
hatch3r-data-classification
Data classification standards covering PII handling, encryption, retention policies, and regulatory compliance.