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 agentmods add skills/lucassantana-dev/sharekit/app-teardownnpx skills add LucasSantana-Dev/sharekit --skill app-teardowngit clone --depth 1 https://github.com/LucasSantana-Dev/sharekitWrote 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/lucassantana-dev/sharekit/app-teardown)<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/app-teardown"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/app-teardown.svg" alt="Measured on agentmods" 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 | $0.00152 | $0.01177 |
| Opus 5 | $0.00076 | $0.00589 |
| Sonnet 5 | $0.00030 | $0.00235 |
| Haiku 4.5 | $0.00015 | $0.00118 |
Grade A, and why
app-teardown 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 5d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Teardown
Studies a live product the way a chef eats at a rival's restaurant: walk the real flows, name what works, explain WHY it works for them, and decide what transfers to our context. The output is a decision artifact, not a tour.
Use When
- A live app/product should be mined for ideas applicable to one of our projects.
- Before building a surface that a named competitor/product already does well.
- User names a product and asks what to learn, steal, or adapt from it.
Do Not Use When
- Target is a repo/codebase →
code-teardown. - Only visual direction is wanted (moodboard, type, palette) →
frontend-reference-hunt. - Understanding OUR OWN system's internals →
doc-and-modernize.
Inputs / Prereqs
- Target URL + whether login is needed (drive the user's Chrome via
claude-in-chrome). - OUR context lock: which project the ideas land in, its goals and constraints.
- Memory state-check FIRST:
reference_<target>_evaluated_*note exists → surface prior outcome and stop unless the revisit condition is met.
Workflow
- Scope + constraint capture — target, key flows to walk, and the gate question: why does their design work FOR THEM (scale, audience, pricing model, compliance, platform, legacy)? Record it; it powers the cargo-cult gate later.
- Live exploration (claude-in-chrome) — walk onboarding, core flow, settings, empty
states, error recovery, upgrade/paywall moments. Screenshot each finding into
<project>/.claude/design/refs/. Note deliberate ABSENCES and simplifications too. - Map by dimension — UX (interaction, feedback, empty/error states), Features (jobs-to-be-done, scope cuts, free-vs-paid line), Visual design (type, spacing, components, motion), Copy (tone, terminology), Growth (activation, referral, retention hooks). 2+ dimensions minimum; skip dimensions irrelevant to the brief.
- State-check per candidate finding — do WE already have it? Query graphify
(
graphify query) when the target project hasgraphify-out/, plus grep/memory. Mark hitsalready-haveinstead of re-proposing them. - Verdict + rationale per finding — apply the contract in
references/teardown-contract.md: evidence,
adopt | adapt | already-have | reject, the mandatory constraint rationale ("[their constraint] → [applies to us?] → [action]"), effort, landing spot in our repo. - Emit + remember — report to
<project>/docs/reference/<target>-teardown-<date>.md(committable). Memory notereference_<target>_evaluated_<date>.mdwith outcome + revisit condition; an "evaluated → nothing" outcome is a valid, valuable result (prevents re-evaluation — megabrain/llmwiki precedent). Summary line: "N findings, A adopt, D adapt, H already-have, R rejected".
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.
- 5d ago First seen · 96 lines · 152 tokens per session scan A 7ce79e67725e
app-teardown is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 5d ago), licensed MIT. It adds 152 tokens to every session and 1,177 once invoked, about $0.0008 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.
Other skills, from other repositories
creating-cursor-rules-skill
Expert guidance for creating effective Cursor IDE rules with best practices, patterns, and examples.
creating-opencode-plugins
Use when creating OpenCode plugins that hook into command, file, LSP, message, permission, server, session, todo, tool, or TUI events - provides plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript event-driven modules.
thoroughness
Use when implementing complex multi-step tasks, fixing critical bugs, or when quality and completeness matter more than speed - ensures comprehensive implementation without shortcuts through systematic analysis, implementation, and verification phases.
Cursor rules for building custom frontends with Momen
Cursor rules for building custom frontends with Momen.app as headless BaaS with GraphQL API, actionflows, AI agents, and Stripe integration.
Cursor rules for Cypress development with accessibility testing
Skill "Cursor rules for Cypress development with accessibility testing" from AmariahAK/atlarix-skills, covering when to use this skill, source, persona, auto-detect typescript usage and accessibility testing focus.
Cursor rules for Helium Mcp
Skill "Cursor rules for Helium Mcp" from AmariahAK/atlarix-skills, covering cursor rules for helium mcp, when to use this skill, source, helium mcp in cursor and enable the server in cursor.