A command that starts or resumes a verification-based website launch process and records the project’s tracking workbook.

Use it to begin or continue a launch, create its tracking record, walk through launch phases, and enforce the pre-launch gate.

It gives a launch a defined scope, tracked phases, and a required approval step before release.

web-launch — Command for Claude Code by hamza-ali-shahjahan/hamzaish

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add hamza-ali-shahjahan/hamzaish

Claude Code

/plugin install web-launch

Made for: Claude Code.

Or install web-launch, the plugin that ships this one along with the rest of its 3 skills, 1 command.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/hamza-ali-shahjahan/hamzaish/web-launch/github.svg)](https://agentmods.dev/commands/hamza-ali-shahjahan/hamzaish/web-launch)

Your own site

<a href="https://agentmods.dev/commands/hamza-ali-shahjahan/hamzaish/web-launch"><img src="https://agentmods.dev/badge/commands/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/hamza-ali-shahjahan/hamzaish/web-launch"><img src="https://agentmods.dev/badge/commands/hamza-ali-shahjahan/hamzaish/web-launch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 722 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00035	$0.00722
Opus 5.5	$0.00014	$0.00289
Sonnet 5.5	$0.00007	$0.00144
Haiku 4.5	$0.00003	$0.00072

Measured 2mo ago against content hash 7033782f9b0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

web-launch 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 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.

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.

factory/plugins/web-launch/commands/web-launch.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The user invoked: /web-launch $ARGUMENTS

Run a website launch as a process, not a to-do list. Load the web-launch skill for the full method; this command is the entry point.

Step 1 — Read the gotchas first

Load the launch-gotchas skill before anything else. The biggest launch risks are known failure modes — recognize them up front, not after they bite.

Step 2 — Scope + stamp the workbook

Identify the launch target from $ARGUMENTS (project name, or a repo path). If unclear, ask: project name, domain, stack, hosting, CDN, CMS, launch date.
Check whether a launch-checklist.md already exists in the target repo.
- Exists → this is a resume. Read it, summarize current Status counts by priority, and jump to Step 4.
- Absent → copy the launch-workbook.md template into the target repo as launch-checklist.md and fill in the Project Info table. The template lives in the web-launch skill's templates/ folder — resolve it as ${CLAUDE_PLUGIN_ROOT}/skills/web-launch/templates/launch-workbook.md when this runs as a plugin, or as templates/launch-workbook.md adjacent to the web-launch SKILL.md when it runs as a plain skill (locate via factory/skills/web-launch/templates/launch-workbook.md). Load the web-launch skill — it points to the same template — if either path is unclear.
Mark stack-irrelevant items N/A up front so the gate math is honest.

Step 3 — Walk the 14 phases

Go phase by phase. Assign an owner to every live item. Delegate commodity work rather than re-deriving it — route per the table in the web-launch skill (searchfit-seo:* for SEO/schema/links/AEO, security-review for the security baseline, pseo-at-scale for large templated page sets). Update Status in place. Remember: Done ≠ Verified — close an item only when its "How to verify" check passes independently.

Step 4 — Sign-off gate verdict

Walk the 24-item Pre-Launch Sign-Off Gate. Produce a clear verdict:

LAUNCH — every P0/P1 is Verified (or a P1 is consciously deferred with reason + owner + revisit date).
DO NOT LAUNCH — list every failing item with its owner and the check it must pass.

Read the full file on GitHub · 34 lines

Changes

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 · 34 lines · 35 tokens per session scan A 7033782f9b0d

Subscribe to this mod's changes

web-launch is a command published in the GitHub repository hamza-ali-shahjahan/hamzaish (10 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 722 once invoked, about $0.0001 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.

Claude Code Project management agent-skills ai-agents buildinpublic claude indie-hacker

web-launch next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
web-launchhamza-ali-shahjahan/hamzaish	Command	10	1mo ago	MIT	A	35	Claude Code
startalifanov/ai-garage-launch	Command	2	3mo ago	MIT	A	28	Claude Code
statusalifanov/ai-garage-launch	Command	2	3mo ago	MIT	A	25	Claude Code
channelalifanov/ai-garage-launch	Command	2	3mo ago	MIT	A	27	Claude Code
launchalifanov/ai-garage-launch	Command	2	3mo ago	MIT	A	19	Claude Code
paymentsalifanov/ai-garage-launch	Command	2	3mo ago	MIT	A	27	Claude Code
specalifanov/ai-garage-launch	Command	2	3mo ago	MIT	A	25	Claude Code