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-ask-as-questionsgit 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-ask-as-questions)<a href="https://agentmods.dev/skills/hani-q/qstack/qstack-ask-as-questions"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-ask-as-questions/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-ask-as-questions"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-ask-as-questions.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 | $0.00127 | $0.01037 |
| Opus 5.5 | $0.00051 | $0.00415 |
| Sonnet 5.5 | $0.00025 | $0.00207 |
| Haiku 4.5 | $0.00013 | $0.00104 |
Grade A, and why
qstack-ask-as-questions 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qstack-ask-as-questions
Turn the open questions in the immediately previous assistant answer into questions a reader outside the work can answer. Ask them one round at a time with the host's structured question tool, and report the answers.
This skill reads the conversation, not the plan. A plan's open-questions
section belongs to /qstack-ask-plan-open-questions, which also writes the
answers back into the plan. This skill writes nothing.
Read the invocation
The argument is free text naming the reader. Take the role from it and, when present, the product that reader owns.
/qstack-ask-as-questions(product manager)/qstack-ask-as-questions ceo/qstack-ask-as-questions support lead on the habit tracker
Choose the lens from the role table in skills/qstack-explain-for/SKILL.md
and follow that table where it sits rather than copying it here. The default
reader is a product manager.
Collect the questions
Read the previous substantive assistant answer. A question is anything that answer leaves for the user to decide: a sentence that asks, a numbered "your call" list, a choice between two named options, or a statement that work is waiting on the user's word. Collect every one. Do not add a question the answer did not raise, and do not drop one because it seems minor.
If the previous answer holds no such question, say so in one short line and stop.
Each question carries what the answer already knows about it: what the choice is, why it came up, what each way costs, and what the answer recommended if it recommended anything. That context is the raw material for the rephrasing; nothing is invented beyond it.
Shape each question
Every question is asked in this shape, in this order:
- The header, when the tool has one: a short label naming the subject, not the question.
For a <role>:the question at the reader's altitude, written under the role's row of the explain-for table. Lead with the reader's silent question from that row. Assume the reader has not seen the work, the files, or the conversation, so carry the context an outsider needs: what was being done, why it stopped on this, and what waits on the answer. Drop file paths and internal names unless the reader has to use them.ELI10:the same question in two or three sentences a ten-year-old follows. A concrete comparison works; jargon does not.Options:letteredA,B,C, and so on, each in the reader's language, each saying what happens if it is picked and what it costs. The recommended option is listed first asAwith(Recommended)in its label and a one-sentence reason in its description. If the previous answer recommended nothing, recommend the option that keeps the most existing decisions intact and say that is why.
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 · 90 lines · 127 tokens per session scan A 5f7197c44086
qstack-ask-as-questions is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 3d ago), licensed MIT. It adds 127 tokens to every session and 1,037 once invoked, about $0.0005 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 2026-09-17.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.