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 albertobarnabo/lazy-cat --skill think-twicegit clone --depth 1 https://github.com/albertobarnabo/lazy-catWrote 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/albertobarnabo/lazy-cat/think-twice)<a href="https://agentmods.dev/skills/albertobarnabo/lazy-cat/think-twice"><img src="https://agentmods.dev/badge/skills/albertobarnabo/lazy-cat/think-twice/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/albertobarnabo/lazy-cat/think-twice"><img src="https://agentmods.dev/badge/skills/albertobarnabo/lazy-cat/think-twice.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 | $0.00158 | $0.01384 |
| Opus 5 | $0.00079 | $0.00692 |
| Sonnet 5 | $0.00032 | $0.00277 |
| Haiku 4.5 | $0.00016 | $0.00138 |
Grade A, and why
think-twice 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 10d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lazy Agent — Work Smarter, Not Harder
"A great engineer is a lazy engineer. They find the clever shortcut." — Steve Jobs
This skill rewires Claude's default instinct. Instead of charging ahead with the most obvious approach, Claude must first ask: "Is there a smarter way to do this?"
Productive laziness is not about doing less. It's about never doing more than necessary.
When NOT to run this checklist
Skip if the task is trivially small (under ~10 lines, no data, no new dependencies) or if the user has explicitly described custom logic that no generic library could cover. In those cases, proceed directly.
Also: never hand-roll cryptography or security primitives. "Use an existing implementation" means the language stdlib or a widely-audited library — not a custom implementation.
The Lazy Check
Run this before any task that feels heavy — a large block of code, repetitive data, a complex algorithm, a long implementation. Stop at the first question that reveals a better path.
1. Am I solving the right problem?
Before writing a single line, make sure the task is correctly understood.
- What is the user actually trying to achieve?
- Am I about to solve a symptom instead of the root cause?
- Would a 2-sentence clarification save 200 lines of code?
If the answer to any of these is uncertain — ask the user before writing any code. One targeted question now saves a full redo later.
2. Is there an existing solution?
Someone has almost certainly solved this before.
- Public API: Does a service already expose this data or functionality at runtime? Prefer it — no maintenance, always up to date.
- Package: Would
npm installorpip installdeliver this in 10 lines instead of 200? - Open dataset: Is there a downloadable file (CSV, JSON, SQLite) from a trusted source?
- Standard library: Does the language's stdlib already cover this?
3. Am I doing too much?
Scope creep is the enemy of efficiency.
- Does the user need all of this, or just a slice?
- Am I precomputing everything when I could compute on demand?
- Am I generating 100 cases when 3 examples would prove the point?
- YAGNI: if it's not needed right now, don't build it.
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.
- 10d ago First seen · 147 lines · 158 tokens per session scan A 5da80bbd424d
think-twice is a skill published in the GitHub repository albertobarnabo/lazy-cat (50 stars, last pushed 3mo ago), licensed MIT. It adds 158 tokens to every session and 1,384 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 2026-08-30.
Other skills, from other repositories
content-strategy
Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning. Use this skill whenever the user wants to plan a content program, define content pillars, build an editorial calendar, structure topic clusters, set up content governance, or align…
stakeholder-communication
Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on…
analytics-strategy
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…
incident-response
Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers…
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
agb-begriff-vorformuliert-305
Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-begriff-vorformuliert-305.