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 liza-mas/liza --skill lean-thinkinggit clone --depth 1 https://github.com/liza-mas/lizaWrote 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/liza-mas/liza/lean-thinking)<a href="https://agentmods.dev/skills/liza-mas/liza/lean-thinking"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/lean-thinking/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/liza-mas/liza/lean-thinking"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/lean-thinking.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 | $0.00045 | $0.01734 |
| Opus 5.5 | $0.00018 | $0.00694 |
| Sonnet 5.5 | $0.00009 | $0.00347 |
| Haiku 4.5 | $0.00005 | $0.00173 |
Grade A, and why
lean-thinking 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 25d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Everything a flow does either delivers what its consumer values, enables that delivery, or is waste. Everything that makes delivery harder than it needs to be is friction. Name both with evidence; the owner decides what to change.
Distinct From
| Skill | Its lens | This skill's lens |
|---|---|---|
code-quality-assessment, clean-code |
Code smells, maintainability | Cost to the flow, not to the code |
systemic-thinking |
Coherence, fragility, future risk | Present cost of how work moves |
context-engineering |
Prompt payload fit | Whole-flow effort, time, rework |
have-you-considered |
Alternative approaches | What to stop, merge, or unblock |
Code-level issues are in scope only when they cost the flow (rework, waiting, relearning) — report that cost, not the smell.
Workflow
1. FRAME THE VALUE STREAM
- Consumer: who receives the output? (end user, next stage, reviewer, agent)
- Value: what would they notice missing? If unclear → ask. Without it, "useless" is undefined.
- Map trigger → delivered value: steps, handoffs, queues, artifacts, loops.
- Mark each step: value-adding | enabling (verification, safety, compliance) | candidate waste.
- Gather evidence: artifacts, logs, git history, timings, retries. Measure where possible
(lead time vs touch time, rework loops, queue durations). Observe the running system
(live state, what actors actually do), not only its declared configuration.
2. SWEEP EVERY CATEGORY (below) — full inventory, no early stop.
3. LOAD-BEARING CHECK each candidate (below).
4. RANK by avoidable cost over a stated horizon: frequency × unit cost (time, tokens, rework,
cognitive load, consumed irreversible inputs), including what it causes downstream. Sunk
cost does not rank. Compare in one unit where conversion is defensible; otherwise rank
within each unit and state the judgement that orders them. Mark each cost measured or
estimated. Findings that feed each other (e.g. retries saturating the lock that blocks
recovery) rank once, as a loop.
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.
- 25d ago First seen · 130 lines · 45 tokens per session scan A 83991a53e16e
lean-thinking is a skill published in the GitHub repository liza-mas/liza (410 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 1,734 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…