qstack-build-the-lever

qstack-build-the-lever is a skill for Claude Code, Codex from hani-q/qstack. It costs 30 tokens per session (454 once invoked), scanned A, original, MIT.

A method for building the smallest repeatable script, generator, query, or check for work that would otherwise be repeated manually.

In plain words
What is it for?
Use it to automate repeated edits or checks, test the process on one item first, support dry runs for risky changes, and verify the resulting files.
Why use it?
It makes non-trivial work easier to rerun, review, and verify. It also reduces duplicate changes and makes failures visible.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/hani-q/qstack/qstack-build-the-lever
Any agent
npx skills add hani-q/qstack --skill qstack-build-the-lever
Clone the repo
git clone --depth 1 https://github.com/hani-q/qstack

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for qstack-build-the-lever

README.md
[![agentmods](https://agentmods.dev/badge/skills/hani-q/qstack/qstack-build-the-lever.svg)](https://agentmods.dev/skills/hani-q/qstack/qstack-build-the-lever)
Your own site
<a href="https://agentmods.dev/skills/hani-q/qstack/qstack-build-the-lever"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-build-the-lever.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 454 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.00454
Opus 5 $0.00015 $0.00227
Sonnet 5 $0.00006 $0.00091
Haiku 4.5 $0.00003 $0.00045

Measured 3d ago against content hash d34e6379f859, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qstack-build-the-lever 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 3d 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.

skills/qstack-build-the-lever/SKILL.md · 41 lines

What it actually says

Build the lever

When authorized work is not a couple of obvious edits, build the smallest tool that performs or proves it instead of repeating the work by hand.

Build one rerunnable artifact

  1. Do one unit manually to learn the real recipe.
  2. Choose the smallest fitting artifact: a script, codemod, generator, query, check, or a single immutable recipe for delegated work. Build a tool, not a framework.
  3. Make reruns safe. Detect current state, avoid duplicate effects, expose failures, and support a dry run when mutations carry meaningful risk.
  4. Run the tool against the first unit and diff its result against the manual version. Resolve any mismatch before applying it broadly.
  5. Use the tool for the remaining scope and keep its output reviewable.
  6. Prove the produced artifacts directly. A deterministic check is part of the lever when it is what makes the work trustworthy.

A deterministic lever beats several people or agents applying the same recipe by hand. If delegation remains useful, give every delegate the same recipe, verification contract, and write fence. Keep that contract outside their write scope.

Applying this skill to authorized non-trivial work produces a rerunnable file. For a read-only request, propose the file and do not create it. Keep every write inside the user's scope. Invocation alone never authorizes a commit, push, publication, deployment, or external message.

Adapted from Lauren Tan's PStack principle-build-the-lever at commit 60c641e4fad674784b30abcf9f8915dea39df38d under the MIT License. See third-party notices.

Files

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.

Changes

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.

  1. 3d ago First seen · 41 lines · 30 tokens per session scan A d34e6379f859

Subscribe to this mod's changes

qstack-build-the-lever is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 7d ago), licensed MIT. It adds 30 tokens to every session and 454 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens