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 skills add hamza-ali-shahjahan/hamzaish --skill web-launchgit 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/skills/hamza-ali-shahjahan/hamzaish/web-launch)<a href="https://agentmods.dev/skills/hamza-ali-shahjahan/hamzaish/web-launch"><img src="https://agentmods.dev/badge/skills/hamza-ali-shahjahan/hamzaish/web-launch/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/skills/hamza-ali-shahjahan/hamzaish/web-launch"><img src="https://agentmods.dev/badge/skills/hamza-ali-shahjahan/hamzaish/web-launch.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 | $0.00118 | $0.01721 |
| Opus 5.5 | $0.00047 | $0.00688 |
| Sonnet 5.5 | $0.00024 | $0.00344 |
| Haiku 4.5 | $0.00012 | $0.00172 |
Grade A, and why
web-launch scanned grade A 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Every item carries its own check.** The "How to verify" column is the contract — a `curl` test, a tool threshold, a score. If you can't state the check, the item isn't ready to track. How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
web-launch
The one rule that makes this work: Done ≠ Verified. An item is
Donewhen someone finished the work. It isVerifiedonly when its objective check passed independently. A redirect can be "working" while the canonical tag is still wrong; a tag can be "installed" while it's missing on the blog. Never close an item on a claim — close it on a check. (See the Done-without-verification gotcha.)
When you activate
- Taking a website or major section to production.
- Someone asks "is this ready to launch?" / "what's left before we ship?"
- Building, stamping, or walking a launch checklist for a project.
- Setting up the post-launch monitoring cadence.
Core model — carry this through every phase
Priority (P0–P4). P0 Blocker = launch cannot proceed until Verified. P1 Critical = must be Verified before launch; deferrable only with a written reason + owner + revisit date. P2 Major = should be done by launch, may slip to week 1. P3 Minor / P4 Nice = post-launch backlog.
Status. Open → In Progress → Done → Verified, plus Blocked, Deferred (with reason + revisit trigger), N/A. Done is not closed. Only Verified is closed.
Every item carries its own check. The "How to verify" column is the contract — a curl test, a tool threshold, a score. If you can't state the check, the item isn't ready to track.
Process
Phase 0 — Scope + stamp. Identify the project, stack, hosting, CDN, CMS, launch date, and site profile (app / content-site / hybrid). Copy templates/launch-workbook.md into the launching project as launch-checklist.md and fill in Project Info. Use the Site-profile table to pre-mark N/A blocks so an app launch isn't bloated with content-site rows (and a hybrid gets its both-surfaces analytics audit). Don't leave skipped items ambiguous — mark them. Read launch-gotchas now — before work starts, not after something breaks.
Where to stamp it: in a standalone repo → the repo root. Inside Hamzaish →
products/<slug>/launch/launch-checklist.md(the product's code repo stays separate and may not be path-wired locally). Log a one-line entry inproducts/<slug>/decisions/.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 79 lines · 118 tokens per session scan A 91c8a5511885
web-launch is a skill published in the GitHub repository hamza-ali-shahjahan/hamzaish (10 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 1,721 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
web-launch compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| web-launchhamza-ali-shahjahan/hamzaish | Skill | 10 | 1mo ago | MIT | A | 118 | Claude Code |
| gingiris-launchGingiris/gingiris-launch | Skill | 216 | 6mo ago | MIT | A | 326 | Claude Code, Codex |
| payments-polaralifanov/ai-garage-launch | Skill | 2 | 3mo ago | MIT | A | 53 | Claude Code |
| stack-referencealifanov/ai-garage-launch | Skill | 2 | 3mo ago | MIT | A | 67 | Claude Code |
| unit-economicsalifanov/ai-garage-launch | Skill | 2 | 3mo ago | MIT | A | 73 | Claude Code |
| traffic-channelsalifanov/ai-garage-launch | Skill | 2 | 3mo ago | MIT | A | 59 | Claude Code |
| make-playbooktamdogood/make-playbook | Skill | 5 | 4mo ago | MIT | A | 97 | Claude Code |