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-stegit 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-ste)<a href="https://agentmods.dev/skills/hani-q/qstack/qstack-ste"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-ste/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-ste"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-ste.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 | $0.00168 | $0.01170 |
| Opus 5.5 | $0.00067 | $0.00468 |
| Sonnet 5.5 | $0.00034 | $0.00234 |
| Haiku 4.5 | $0.00017 | $0.00117 |
Grade A, and why
qstack-ste 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 26d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qstack-ste
Rewrite the immediately previous assistant answer in Simplified Technical English. Keep every fact, decision, warning, and next action. Keep the same reader and roughly the same length. Output only the rewrite.
This skill changes wording only. /qstack-be-concise changes length,
/qstack-explain-for changes the reader, /qstack-unslop removes AI writing
patterns. Chain them when more than one is wanted.
Read the level
The argument is a whole number from 1 to 100. It snaps to a tier. No argument means 80.
| Argument | Tier | What it applies |
|---|---|---|
| 1 to 60 | light | The core rules below |
| 61 to 90 | standard | Core rules plus the sentence rules: 20 words for an instruction, 25 for a description, one instruction per sentence, present tense for descriptions, no -ing verb forms |
| 91 to 100 | full | Standard plus the word rules: only words from the STE dictionary and technical names, one approved meaning per word, no synonyms for the same thing |
The full rule lists for each tier are in references/rules.md. Read that file before the first rewrite in a session.
Core rules, every tier
- The first sentence is the answer: yes or no, done or not done, ready or not ready, or the number asked for. The reason comes after it.
- Active voice, and the actor is named: "I pushed it", "You merge it", not "It remains unmerged".
- One name per thing, and the user's name for it when they gave one. Card numbers, spec sections, commit hashes, and symbol names are left out unless the reader needs them to act. A needed one is explained in plain words the first time.
- A noun cluster has at most three words: "the check that rejects rc versions", not "the root version validator".
- Something the reader must do is a command, one per sentence, condition first: "If the review scores 5/5, merge PR 144." If nothing is needed from the reader, one line says so.
- One topic per paragraph, at most six sentences per paragraph. Status from other work is not appended to an answer.
- List numbers stay as they were in the previous answer. A dropped item is marked dropped, not renumbered.
What ships with it
2 files 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.
- 26d ago First seen · 92 lines · 168 tokens per session scan A 34a0a95f8fc4
qstack-ste is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 3d ago), licensed MIT. It adds 168 tokens to every session and 1,170 once invoked, about $0.0007 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 2026-10-03.
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…