qstack-how

A read-only code-walkthrough skill that explains how a subsystem runs by tracing its entry points, files, callers, data changes, and boundaries. It can also critique architecture when the user explicitly asks for that.

In plain words
What is it for?
Use it for onboarding, runtime-flow explanations, architecture walkthroughs, placement questions, and explicitly requested architecture critiques. It records the paths and symbols it was able to trace.
Why use it?
It helps developers build a concrete mental model of unfamiliar code without presenting guesses as facts. It does not edit, fix, commit, publish, deploy, or message anyone.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/hani-q/qstack/qstack-how
Any agent
npx skills add hani-q/qstack --skill qstack-how
Clone the repo
git clone --depth 1 https://github.com/hani-q/qstack

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 541 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.00541
Opus 5 $0.00022 $0.00270
Sonnet 5 $0.00009 $0.00108
Haiku 4.5 $0.00004 $0.00054

Measured yesterday against content hash 17b43f62837c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qstack-how 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 yesterday.

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.

skills/qstack-how/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QStack how

Build a working mental model from the code. This skill is read-only. It does not edit files, fix critique findings, commit, push, publish, deploy, or message anyone.

Choose the mode

  • Explain is the default. Answer how the system works and where behavior lives.
  • Critique runs only when the user asks for architectural problems or improvements. Explain the system first, then critique it.

This skill explains mechanism, placement, and ownership. Label inferred motivation as inference instead of presenting it as historical fact.

Investigate

  1. Resolve the subject and scope. For harmless ambiguity, state a reasonable interpretation and proceed. Ask only when different interpretations would materially change the answer.
  2. Search for the entry point and read the implementation. Trace callers, callees, state changes, data transformations, types, and boundaries until the path from trigger to effect has no hand-waved step.
  3. Check repository instructions, configuration, generated code, tests, and external boundaries that change the flow. Do not infer behavior from names.
  4. Record exact paths, symbols, and lines. State any path that could not be traced.

Handle a narrow question directly. For a cross-cutting subsystem, read complex exploration. When the answer needs a full onboarding narrative, read structured explanation.

Present

Lead with the direct answer. Then include only the concepts, flow, file map, and gotchas needed to make it understandable. Use a diagram when it materially clarifies several components or state transitions.

For Critique mode, read architecture critique only after the explanation is grounded in the code. Report findings and tradeoffs; do not apply fixes.

Adapted from Lauren Tan's PStack how at commit 60c641e4fad674784b30abcf9f8915dea39df38d under the MIT License. See third-party notices.

Read the full file on GitHub · 57 lines

Files

What ships with it

4 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.

Changes

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.

  1. yesterday First seen · 57 lines · 43 tokens per session scan A 17b43f62837c

Subscribe to this mod's changes

qstack-how is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 541 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens