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/security-check)<a href="https://agentmods.dev/commands/hamza-ali-shahjahan/hamzaish/security-check"><img src="https://agentmods.dev/badge/commands/hamza-ali-shahjahan/hamzaish/security-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/security-check"><img src="https://agentmods.dev/badge/commands/hamza-ali-shahjahan/hamzaish/security-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 | $0.00079 | $0.02955 |
| Opus 5.5 | $0.00032 | $0.01182 |
| Sonnet 5.5 | $0.00016 | $0.00591 |
| Haiku 4.5 | $0.00008 | $0.00296 |
Grade A, and why
security-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 19d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user invoked: /security-check $ARGUMENTS
A fast, mechanical baseline audit — not a substitute for the full pre-launch
review in factory/agents/mvp/security-reviewer/ (run that before real users).
This catches the cheap, high-signal config mistakes that AI-generated repos ship
silently. Companion to /ship and docs/security.md.
If $ARGUMENTS is empty, ask which product (or Read ${HAMZAISH_ROOT:-$HOME/Claude/Hamzaish}/products/_portfolio.md to list). Resolve the code path from
${HAMZAISH_ROOT:-$HOME/Claude/Hamzaish}/products/$ARGUMENTS/product.config.json → code_path (the code lives at the absolute path it maps to). Run the checks in that product's code repo.
Fleet mode (when subagent spawning is available)
Per factory/playbooks/mvp-stage/fleet-patterns.md: run the categories below as blind parallel workers (one per numbered section, each seeing only the repo + its own section), then — before any FAIL becomes a BLOCK — spawn a refuter per would-be blocker whose job is to disprove it ("default to refuted if uncertain"; verifiers run on the top model tier). Only findings that survive refutation block; unverifiable ones are reported as unverified, never silently dropped. Serial execution (below, in order) remains fully valid and is the headless default — same verdict format either way.
Run these checks
0. Backend reality check (is there even a backend? — do this FIRST)
A site can look fully static / "no backend" when its backend is env-gated —
the data/auth client only initializes when env vars are present and degrades to
local-only when absent. Never conclude "fully static / no backend / scales
trivially" from a keyless code read — the keyed/production state is the truth.
First-timer rule: if the site has a sign-in button, a save/share feature, or an
admin page, it HAS a backend — open the .env and check.
- Read
.env,.env.local,.env.production,.env.example— populated keys = the backend is LIVE in prod even if the code path is conditional. - Grep deps + src for backend SDKs even when usage is conditional:
supabase,@clerk,firebase, auth libs,prisma/drizzle/any DB client, server SDKs. - Check hosting config (
vercel.json,netlify.toml,next.config.*) for rewrites/proxies to OTHER deployments — a "static" route can front a separate app with its own scale limits. - A site documented/claimed as "static" or "no backend" while env vars + a backend SDK say otherwise = FAIL (the verdict is graded on the wrong state). If a backend exists, then audit the scale ceilings: auth/SMTP rate limits, DB tier limits (connections/auto-pause/storage), and RLS (below). Full required list:
factory/playbooks/mvp-stage/security-checklist.md→ Backend reality check.
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.
- 19d ago Changed · +19 lines 43645deaee82
- 1mo ago First seen · 155 lines · 79 tokens per session scan A 0b668993f3f0
security-check is a command published in the GitHub repository hamza-ali-shahjahan/hamzaish (11 stars, last pushed 19d ago), licensed MIT. It adds 79 tokens to every session and 2,955 once invoked, about $0.0003 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 2026-09-03.
Other commands, from other repositories
dart-fix-ci
Command "dart-fix-ci" from dartsim/dart, covering required reading, workflow and output.
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
check-release-health
Summarize the CI health of an OpenShift release using live data from the openshift-ci-mcp server.
release-manager
Automated release coordination and deployment with ruv-swarm orchestration for seamless version management, testing, and deployment across multiple packages.
cf-scaffold-project
Scaffold a Cloudflare project — Worker, Pages, or Worker+D1+R2 starter — with Wrangler config, Terraform skeleton, and GitHub Actions deploy using scoped API tokens.
dbt-build
Run the fixed governed dbt shadow build under an accepted plan.