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 agentmods add skills/hani-q/qstack/qstack-ask-plan-open-questionsnpx skills add hani-q/qstack --skill qstack-ask-plan-open-questionsgit clone --depth 1 https://github.com/hani-q/qstackWhat 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 | $0.00107 | $0.01969 |
| Opus 5 | $0.00053 | $0.00984 |
| Sonnet 5 | $0.00021 | $0.00394 |
| Haiku 4.5 | $0.00011 | $0.00197 |
Grade A, and why
qstack-ask-plan-open-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 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.
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qstack-ask-plan-open-questions
Turn a plan's unresolved choices into explicit decisions the next reader can trust. Ask only questions whose answers change what gets built or how it can be executed.
Resolve the plan
- Use the supplied path when present.
- Otherwise use a plan clearly referenced in the conversation.
- Otherwise inspect
qstack/compound_engineering/plans/*/plan.html, followed by legacycompound-engineering/plans/*/plan.htmlandplan.mdfiles. Use the only plausible candidate; ask when more than one is plausible or none is. Never select.template/.
Accept .html and .md files only. Read the whole plan and the repository's
instruction files before asking anything.
Reject template, stencil, and example artifacts even when explicitly supplied,
including anything inside .template/ and an uninstantiated
plan-template.html. Report that the file is not an instantiated plan and ask
for the rendered plan path. Do not reinterpret placeholder copy as a real open
question.
Authority
- A supplied Markdown file is a working draft only. Edit it in place when no corresponding HTML plan exists yet.
- Once a corresponding
plan.htmlexists, it is authoritative. Operate on the HTML even if the user supplied the old Markdown path, and tell them which file was selected. - Never synchronize answers back from HTML to Markdown. Never maintain both.
- Never regenerate or overwrite an existing authoritative HTML plan from stale Markdown.
Use a corresponding HTML plan only when the relationship is unambiguous from the standard plan directory, document title, or the current conversion context. Ask rather than guessing between plausible files.
Frozen plans
Before editing an HTML plan, check its directory for execution.md, legacy
implementation-notes.md, outcome.md, the retired board.jsonl, or a
board-events.js containing any call after its required
{"event":"board","format":1} header. If any exists, stop: execution has
started and the plan is frozen. A header-only event stream is the pre-board
placeholder and does not freeze the plan. Decisions made after that point
belong in the execution record through an execution-loop skill, not in
historical plan text.
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.
- 3d ago First seen · 205 lines · 107 tokens per session scan A 98c7fbdab5b4
qstack-ask-plan-open-questions is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 6d ago), licensed MIT. It adds 107 tokens to every session and 1,969 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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…