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/hamza-ali-shahjahan/hamzaishWrote 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/commands/hamza-ali-shahjahan/hamzaish/legal-check)<a href="https://agentmods.dev/commands/hamza-ali-shahjahan/hamzaish/legal-check"><img src="https://agentmods.dev/badge/commands/hamza-ali-shahjahan/hamzaish/legal-check/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/commands/hamza-ali-shahjahan/hamzaish/legal-check"><img src="https://agentmods.dev/badge/commands/hamza-ali-shahjahan/hamzaish/legal-check.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 | $0.00089 | $0.01430 |
| Opus 5.5 | $0.00036 | $0.00572 |
| Sonnet 5.5 | $0.00018 | $0.00286 |
| Haiku 4.5 | $0.00009 | $0.00143 |
Grade A, and why
legal-check 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 16d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user invoked: /legal-check $ARGUMENTS
Six legal traps ship by default in AI-built apps, each fined per child, visitor,
session, email, renewal or work — how zero sales becomes a six-figure exposure. This
command finds them, separates real ones from regex noise, and (with --fix) fixes the
real ones on a branch and opens a PR. Knowledge: factory/playbooks/launch-stage/legal-launch-traps.md
(read it first — it holds each fix and its "done when" test). Detection only, with
no fixing, also runs inside /security-check § 7a and blocks /ship.
Resolve the target(s)
<slug>→${HAMZAISH_ROOT:-$HOME/Claude/Hamzaish}/code-paths.local.json→ the product's code path.- A path → use it directly (works on any repo, Hamzaish-built or not).
--all→ every product incode-paths.local.json. Several products? Run one worker per product in parallel when subagents are available, each with only its own repo (factory/playbooks/mvp-stage/fleet-patterns.md); serial is fine otherwise.- Nothing given → ask which product.
1 · Scan
bun ${HAMZAISH_ROOT:-$HOME/Claude/Hamzaish}/scripts/check-legal-traps.ts <code_path>
Exit 1 only means a FAIL was found.
2 · Verify every FAIL and WARN — the scanner is regex, you are the judge
Open each evidence file:line and decide if the trap is real. Common false calls:
seed/demo data and tool catalogs that merely name Hotjar or "newsletter"; a pricing
mock with no real checkout; a file input that only reads a CSV in the browser; a
"Sign up" link to a page that doesn't exist. Common misses: signup through server
actions or custom email-code auth, a font URL built in JS, a replay snippet in
index.html, a subscription via a payment link.
Also note what the repo is: a deployed product, a prototype, a CLI, a skills-only repo, or a game. And whether it could be directed at children: an age gate does not satisfy COPPA for a child-directed service, so flag that for the operator, don't "fix" it.
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.
- 16d ago First seen · 99 lines · 89 tokens per session scan A 54d7f89fa4cf
legal-check is a command published in the GitHub repository hamza-ali-shahjahan/hamzaish (11 stars, last pushed 16d ago), licensed MIT. It adds 89 tokens to every session and 1,430 once invoked, about $0.0004 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 2026-10-08.
Other commands, from other repositories
au-pspf
You are an enterprise architect generating a Protective Security Policy Framework (PSPF) compliance assessment for an Australian Government entity or contractor handling government information.
compliance-audit
Full regulatory compliance audit for GDPR, HIPAA, SOC2, PCI-DSS, ISO 27001, and other frameworks with gap analysis, remediation planning, and evidence collection.
rgpd
Questões de RGPD e violação de dados — referência, playbook e checklist. GDPR and data-breach matters — reference, playbook and checklist.
arckit.fr-rgpd
You are helping an enterprise architect generate a French CNIL Compliance Assessment — the French-specific GDPR layer applied by the CNIL (Commission Nationale de l'Informatique et des Libertés). Run this after /arckit:eu-rgpd to add French obligations that go beyond the EU GDPR baseline.
india-checklist
Interactive non-code compliance checklist — business registration, DPO, GST, CERT-In, grievance officer, and more.
atrs
Generate Algorithmic Transparency Recording Standard (ATRS) record for AI/algorithmic tools.