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-nextnpx skills add hani-q/qstack --skill qstack-nextgit 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 | $0.00063 | $0.00889 |
| Opus 5 | $0.00032 | $0.00445 |
| Sonnet 5 | $0.00013 | $0.00178 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade B, and why
qstack-next scanned grade B with 1 finding 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
The listing command in `/qstack` prints them; `ls ~/.claude/skills How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qstack-next
Say what was just done, what that leaves undone, and the one skill that closes the gap. Three or four lines. Name the skill; never run it.
Evidence, heaviest first
- The plan folder. Files on disk say where the work is more reliably than the conversation does. See the table below.
- The working tree.
git branch --show-current,git status --short,git log --oneline -5. Uncommitted changes mean work that is not yet verified or reviewed. - The conversation. What the user asked last, what was produced, what was verified. Facts, not tone: "it's broken" followed by three guards and no reproduction is evidence; a frustrated message is not.
Read what you need and no more. This skill is read-only.
The plan lifecycle
Plan folders are qstack/compound_engineering/plans/<slug>/, or the legacy
compound-engineering/plans/<slug>/. The folder whose slug matches the branch
or the conversation is the one that matters. Its files arrive in a fixed
order, and the first one missing is the next step:
| The folder has | Run next |
|---|---|
| Nothing yet, and the user is describing a feature or change | /qstack-plan-prior-art, then draft plan.md |
plan.md and no plan.html |
/qstack-plan-to-html |
plan.html with notes at data-status="open" |
/qstack-ask-plan-open-questions |
plan.html and no board-events.js, or a board without its complete-breakdown marker |
/qstack-plan-to-html to finish the board |
board-events.js with cards still open |
the execution loop execution.md shows was used; /qstack-loop-no-nonsense when it shows none |
every card closed and no outcome.md |
/qstack-plan-adherence-review, then /qstack-plan-close |
outcome.md |
nothing from the lifecycle |
Work with no plan folder and no feature being described is outside the lifecycle; do not push it in.
Outside the lifecycle
Match the conversation against the description: of every installed skill.
The listing command in /qstack prints them; ls ~/.claude/skills ~/.codex/skills ~/.agents/skills names them. Each description says when its
skill applies; that text is the rule, so this file does not repeat it.
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.
- yesterday First seen · 84 lines · 63 tokens per session scan B 090d2e4874f7
qstack-next is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 5d ago), licensed MIT. It adds 63 tokens to every session and 889 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). 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…