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 hani-q/qstack --skill qstack-build-the-levergit clone --depth 1 https://github.com/hani-q/qstackWrote 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/hani-q/qstack/qstack-build-the-lever)<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/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/hani-q/qstack/qstack-build-the-lever"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-build-the-lever.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 | $0.00030 | $0.00454 |
| Opus 5.5 | $0.00012 | $0.00182 |
| Sonnet 5.5 | $0.00006 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00045 |
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 1mo 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.
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
- Do one unit manually to learn the real recipe.
- 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.
- Make reruns safe. Detect current state, avoid duplicate effects, expose failures, and support a dry run when mutations carry meaningful risk.
- Run the tool against the first unit and diff its result against the manual version. Resolve any mismatch before applying it broadly.
- Use the tool for the remaining scope and keep its output reviewable.
- 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.
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.
- 1mo ago First seen · 41 lines · 30 tokens per session scan A d34e6379f859
qstack-build-the-lever is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 454 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.