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-loop-trequartistanpx skills add hani-q/qstack --skill qstack-loop-trequartistagit 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 | $0.00031 | $0.04386 |
| Opus 5 | $0.00015 | $0.02193 |
| Sonnet 5 | $0.00006 | $0.00877 |
| Haiku 4.5 | $0.00003 | $0.00439 |
Grade A, and why
qstack-loop-trequartista 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.
How it starts
The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qstack-loop-trequartista
Treat the plan as the shape of play, not a cage. Preserve its intent while making careful, visible adaptations when reality offers a better route.
Resolve the plan
- Use the supplied plan path when present.
- Otherwise use a plan clearly referenced in the conversation.
- Otherwise inspect
qstack/compound_engineering/plans/*/plan.html, plus legacycompound-engineering/plans/*/plan.htmlandplan.mdfiles. Use the only plausible candidate; ask if more than one is plausible or none exists. Never select.template/.
Resolve the repository root, read its instruction files, then read the whole plan. Do not edit the plan: it is frozen once execution begins.
Verify approval before implementation. An explicit request to execute this
specific plan counts as approval to start only when the plan itself is not
marked draft, proposed, or otherwise unapproved and has no unresolved
blocking gate. If approval is absent or contradictory, stop and ask.
Choose the review mode
Review depth is the user's cost and quality choice. Resolve the plan, detect
whether it has a board, inspect any existing execution.md, and read plan and
repository review requirements without writing anything. Then settle the mode
before creating or updating execution files, migrating or claiming a board,
launching an agent, or editing implementation files.
--review full|final|none supplies the choice for automation. Reject any other
value. Always validate an existing execution.md first, with or without the
flag:
- if
Review modeis present, it appears exactly once and must befull,final, ornone; - no such field means a legacy
fullrun and is not rewritten merely to backfill the field; - a duplicated, malformed, or unknown value stops preflight without mutation.
Without the flag, reuse that recorded or legacy mode without asking. With the flag, it must match that mode as described below. For a new execution without the flag, ask one startup question, using the host's structured question tool when available and plain text when it is not. With a board, ask:
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 · 406 lines · 31 tokens per session scan A 0064bef233d0
qstack-loop-trequartista is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 4,386 once invoked, about $0.0002 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…