launch-check

launch-check is a skill for Claude Code from craigcossairt/trellis. It costs 55 tokens per session (530 once invoked), scanned A, original, MIT.

A checklist for auditing an application before a demo, launch, or user interview. It checks for test data, broken screens, missing loading or error states, and inconsistent branding.

In plain words
What is it for?
Use it to review demo flows, remove development leftovers, and check empty, offline, loading, and error states.
Why use it?
It helps find visible problems and unfinished behavior before other people see the application.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it to review demo flows, remove development leftovers, and check empty, offline, loading, and error states.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/craigcossairt/trellis/launch-check
Install

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.

Any agent
npx skills add craigcossairt/trellis --skill launch-check
Clone the repo
git clone --depth 1 https://github.com/craigcossairt/trellis

Made for: Claude Code.

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.

agentmods badge for launch-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/craigcossairt/trellis/launch-check.svg)](https://agentmods.dev/skills/craigcossairt/trellis/launch-check)
Your own site
<a href="https://agentmods.dev/skills/craigcossairt/trellis/launch-check"><img src="https://agentmods.dev/badge/skills/craigcossairt/trellis/launch-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 530 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.00530
Opus 5 $0.00028 $0.00265
Sonnet 5 $0.00011 $0.00106
Haiku 4.5 $0.00006 $0.00053

Measured 8d ago against content hash 86caf53550a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

launch-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 8d 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.

.claude/skills/launch-check/SKILL.md · 66 lines

What it actually says

You are running a pre-demo audit. This ensures the app is presentable for user interviews, investor pitches, or a launch.

Audit Steps

1. Test Data Cleanup

Check for and flag any test/dev artifacts that would look unprofessional:

  • Search for hardcoded test emails, phone numbers, or names in the codebase
  • Search for TODO, FIXME, HACK, XXX in screens/pages that are part of the demo flow
  • Check for debug print/log statements in production code paths
grep -rn "TODO\|FIXME\|HACK\|XXX" <source-dir> | head -20
grep -rn "console\.log\|debugPrint\|print(" <source-dir> | head -20

2. Critical Screen Audit

Review each screen in the demo flow for polish (no layout overflow, no missing states):

  • Entry point (splash / landing / login)
  • Core flow screen 1
  • Core flow screen 2
  • Settings / profile

3. Error State Coverage

For each critical screen, verify:

  • Empty state exists and is user-friendly (not blank or an error)
  • Network error handling (what happens offline?)
  • Loading states (skeleton/spinner, not blank white)

4. Brand Consistency

  • Brand colors used consistently
  • Correct fonts for headings and body
  • Logo displays correctly
  • No default framework placeholder icons visible

5. Static Analysis

# FILL IN: your lint/typecheck command, e.g. `npm run lint` or `flutter analyze`

Output Format

Produce a report with:

  • PASS items (confirmed good)
  • WARN items (minor, won't break the demo but should fix)
  • FAIL items (must fix before demo)

End with a prioritized fix list for any FAIL items.

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.

  1. 8d ago First seen · 66 lines · 55 tokens per session scan A 86caf53550a5

Subscribe to this mod's changes

launch-check is a skill published in the GitHub repository craigcossairt/trellis (4 stars, last pushed 18d ago), licensed MIT. It adds 55 tokens to every session and 530 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

lov-fix-until-no-error

A verification-focused debugging workflow that repeatedly runs specified checks, fixes the highest-priority failure, and stops when the checks pass or a genuine external blockage remains.

lovstudio/skills · 48 tokens

template-formal

Strongly-typed multiagent ant-robot colony exemplar — ADTs, session-typed protocols, affine-discipline resource handles, storage-as-functor framing, Active-Inference-flavored decision loop, mypy-as-oracle negative controls.

docxology/template · 53 tokens

template-reproducibility-audit

Deterministic reproducibility audit — fixed seeds, regenerate-from-clean, double-run diff before Zenodo/arXiv/release. USE WHEN outputs drift between runs, "worked on my machine", need regenerate-from-clean proof, or pre-release reproducibility check — even without naming docs/prompts.

docxology/template · 70 tokens

template-test-creation

Create pytest suites under the no-mocks policy — real data, temp files, subprocess, pytest-httpserver. USE WHEN adding tests, raising coverage, testing new src/ module, or user forbids mocks.

docxology/template · 47 tokens

infrastructure-benchmark

Deterministic benchmark harnesses for public template exemplars. Use when scoring generated project outputs against benchmark manifests, refreshing the default template smoke manifest, checking publication-readiness rubrics, or adding bounded no-network readiness checks for public template outputs.

docxology/template · 53 tokens

infrastructure-sia

Skill for the Self-Improvement Agent (SIA) harness contract. Use when validating task public/private layouts, generation artifact trees, evaluation runners, fixture replay loops, or opt-in live Meta→Target→Feedback cycles in template projects.

docxology/template · 53 tokens