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 yuri-semenenko/ai-engineering-workspace --skill lazygit clone --depth 1 https://github.com/yuri-semenenko/ai-engineering-workspaceWrote 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/yuri-semenenko/ai-engineering-workspace/lazy)<a href="https://agentmods.dev/skills/yuri-semenenko/ai-engineering-workspace/lazy"><img src="https://agentmods.dev/badge/skills/yuri-semenenko/ai-engineering-workspace/lazy/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/yuri-semenenko/ai-engineering-workspace/lazy"><img src="https://agentmods.dev/badge/skills/yuri-semenenko/ai-engineering-workspace/lazy.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 | $0.00136 | $0.00813 |
| Opus 5 | $0.00068 | $0.00407 |
| Sonnet 5 | $0.00027 | $0.00163 |
| Haiku 4.5 | $0.00014 | $0.00081 |
Grade A, and why
lazy 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lazy
Force the simplest, shortest, most minimal solution that still satisfies the requirement. The best code is the code you never wrote. This operationalizes the persona's "Simplicity wins" / anti-over-engineering bias into a concrete decision ladder applied before generating code.
Decision ladder (stop at the first rung that works)
- Does it need to exist? Can the requirement be dropped, deferred, or met by an existing path? (YAGNI)
- Standard library — does the language stdlib already solve it?
- Native platform — browser API, DB constraint, OS tool, framework primitive?
- Already-installed dependency — reuse what the repo already pulls in; do not add a new dep for a few lines.
- One-liner — can it be a single expression?
- Minimal implementation — only now write the smallest working version.
Rationalizations
Pre-written rebuttals to the excuses that precede over-building. If you catch yourself thinking the left column, the right column is the answer.
| Rationalization | Rebuttal |
|---|---|
| "We'll need this flexibility later." | YAGNI. Build it when later arrives — you'll know the real shape then. |
| "An abstraction makes this cleaner." | Two call sites don't justify a layer. Inline until the third forces the shape. |
| "A small dependency is easier than writing it." | A dep is a supply-chain and upgrade liability. For a few lines, the stdlib rung wins. |
| "This is the idiomatic / enterprise pattern." | Patterns serve problems, not vice versa. Name the problem this one solves here. |
| "It's only a few extra lines." | Every line is maintenance. The default is zero; each line must earn its place. |
Intensity
- lite — build it as asked; mention the lazier path in one line, do not enforce.
- full (default) — enforce the ladder strictly; ship the shortest correct diff; reject speculative abstractions and boilerplate.
- ultra — YAGNI extremist: challenge whether the task should exist at all before writing anything, then ship the absolute minimum. Push back on requirements that smell speculative.
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.
- 8d ago First seen · 47 lines · 136 tokens per session scan A de8867238494
lazy is a skill published in the GitHub repository yuri-semenenko/ai-engineering-workspace (1 stars, last pushed 8d ago), licensed MIT. It adds 136 tokens to every session and 813 once invoked, about $0.0007 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
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
My Skill
Content here.
task-generation
Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.
implementation-standards
Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (.github/agents/developer.md); not directly invokable.
spec-authoring
Reference material for writing product, technical, and operational specifications (work-item priorities, requirement families, success criteria). Loaded on demand by specify-feature; not directly invokable.
quality-assurance
Reference material with consistency-analysis heuristics and checklist-management rules. Loaded on demand by analyze-compliance and quality-control; not directly invokable.