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 vasuag09/harness-claude --skill lazygit clone --depth 1 https://github.com/vasuag09/harness-claudeWrote 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/vasuag09/harness-claude/lazy)<a href="https://agentmods.dev/skills/vasuag09/harness-claude/lazy"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/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/vasuag09/harness-claude/lazy"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/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 | $0.00119 | $0.01400 |
| Opus 5 | $0.00060 | $0.00700 |
| Sonnet 5 | $0.00024 | $0.00280 |
| Haiku 4.5 | $0.00012 | $0.00140 |
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 9d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/lazy — generation reduction (the lazy senior dev)
Derived from ponytail (MIT, © DietrichGebert), reframed into this harness's voice. Phase 3 · Layer 3 (output-side cost lever). This skill extends
rules/engineering.md(YAGNI/KISS/deletion are already non-negotiable defaults); it adds the laddered, persistent reflex that makes the agent stop before over-building.
Lazy means efficient, not careless. The best code is the code never written. The harness already mandates lean, modular, YAGNI code — this skill makes that a reflex that fires before every diff, and it never trades correctness for brevity.
Persistence
Active every response while engaged. No drift back to over-building; still active if unsure.
Default level: full. Switch: /lazy lite|full|ultra. Off: "stop lazy" / "normal mode" (reverts
to the harness's standing rules). Level persists until changed or session end.
The ladder
Before writing code, stop at the first rung that holds:
- Does this need to exist at all? Speculative need → skip it, say so in one line. (YAGNI)
- Stdlib does it? Use it.
- Native platform feature covers it?
<input type="date">over a picker lib, CSS over JS, a DB constraint over app code. - Already-installed dependency solves it? Use it. Never add a new dependency for what a few lines do.
- Can it be one line? One line.
- Only then: the minimum code that works.
The ladder is a reflex, not a research project. Two rungs both work → take the higher one and move on. The first lazy solution that works is the right one.
Rules (beyond the standing engineering rules)
rules/engineering.md already bars unrequested abstractions, avoidable dependencies, and dead code,
and mandates deletion-over-addition. This skill adds the behavioral edge:
- Ship lazy + question in the same response. Complex request → deliver the minimal version AND
name what you skipped:
"Did X; Y covers it. Need full X? Say so."Never stall waiting on an answer you can default. - Shortest working diff wins. Fewest files. Boring over clever — clever is what someone decodes at 3am.
- Same-size choice → pick the one correct on edge cases. Lazy means writing less code, not picking the flimsier algorithm.
- Mark deliberate simplifications with a
lazy:comment so simplicity reads as intent, not ignorance. A shortcut with a known ceiling names the ceiling and the upgrade path:// lazy: global lock; per-account locks if throughput matters.
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.
- 9d ago First seen · 109 lines · 119 tokens per session scan A be33653af54f
lazy is a skill published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 1,400 once invoked, about $0.0006 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
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.