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-serve-plansnpx skills add hani-q/qstack --skill qstack-serve-plansgit 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 | $0.00025 | $0.00519 |
| Opus 5 | $0.00013 | $0.00260 |
| Sonnet 5 | $0.00005 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
qstack-serve-plans 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 2d 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
/qstack-serve-plans
Start an HTTP server for the current repository's QStack plans and report the URL. Do not edit the repository.
Run
- Resolve the repository root with
git rev-parse --show-toplevel; fall back to the current directory outside Git. - Collect the bind IP address and port before starting anything. Treat values
explicitly supplied by the user as answers and ask for every missing value,
preferably in one prompt. Offer
127.0.0.1as the recommended local-only address, explain that0.0.0.0exposes the server on all interfaces, and offer8000as the recommended port. Never infer network exposure or silently choose a port. - Require a non-empty address and a numeric port from
1through65535. - Require
qstack/compound_engineering/. If it is missing, say that this repository has no QStack plans yet and stop. - If the selected address and port cannot be bound, report that and ask the user for another address or port. Do not select a replacement silently.
- Start the server as a long-running background process using the harness's process controls. Do not write PID or log files into the repository.
Prefer the project script when it accepts both arguments:
bash <repo-root>/qstack/scripts/serve.sh <port> <bind-address>
If the script is missing or only supports the legacy port argument, fall back without modifying the repository:
python3 -m http.server <port> --bind <bind-address> \
--directory <repo-root>/qstack/compound_engineering
Verify the server responds at http://<bind-address>:<port>/. When binding to
0.0.0.0, verify through 127.0.0.1 and report that it is listening on all
interfaces. Report the root URL and, when there is exactly one plan, its direct
/plans/<slug>/plan.html URL, plus /plans/<slug>/plan.html#board when that
plan directory holds a board-events.js. Keep the final response to one or two
lines.
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.
- 2d ago First seen · 50 lines · 25 tokens per session scan A 7bfe9a613bae
qstack-serve-plans is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 519 once invoked, about $0.0001 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…