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-plan-closenpx skills add hani-q/qstack --skill qstack-plan-closegit 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 | $0.00021 | $0.01798 |
| Opus 5 | $0.00010 | $0.00899 |
| Sonnet 5 | $0.00004 | $0.00360 |
| Haiku 4.5 | $0.00002 | $0.00180 |
Grade A, and why
qstack-plan-close 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.
How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qstack-plan-close
Turns a finished piece of work into compounding knowledge.
The plan is not the lesson. The lesson is the delta between the plan and reality: what diverged, what surprised you, what cost hours that nothing predicted. This skill captures that delta and writes it where the next plan in this area will read it.
The convention
qstack/compound_engineering/plans/<feature-slug>/
├── plan.html # BEFORE: what we predicted. Frozen once work starts.
├── board-events.js # DURING: append-only card events, written by agents.
├── execution.md # DURING: decisions, deviations, validation, and reviews.
└── outcome.md # AFTER: this skill writes it.
If the repo has qstack/compound_engineering/README.md, read it first: it may
extend or override what follows. Also support the legacy
compound-engineering/plans/<feature-slug>/ layout and its README. Prefer the
QStack layout when both contain the requested feature. If neither plan root
exists, offer to create the QStack layout before proceeding.
Hard rules
- Never edit
plan.htmlor legacyplan.md. The plan is frozen once work starts; divergence is recorded inoutcome.md, not by rewriting history. - Never commit. Write files and stop. The user commits.
- Do not implement anything. This skill only writes documentation.
Steps
1. Identify the plan folder
ls qstack/compound_engineering/plans/
ls compound-engineering/plans/ # legacy, when present
If the user named a feature, use it. If not, infer from the current branch and recent commits, then confirm with the user before writing.
2. Establish ground truth
Do not rely on the plan's claims. Gather what actually happened:
git log --oneline --format='%h %ad %s' --date=short -20 -- <paths the plan touched>
git log --all --oneline --diff-filter=A -- '<resolved-plan-folder>/*'
Then verify the shipped surface exists: ls the scripts, grep for the key
symbols the plan promised. A plan that says it shipped foo_bar() and a tree
with no foo_bar() is the single most valuable finding this skill can produce.
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 · 176 lines · 21 tokens per session scan A 3e8e001b73ef
qstack-plan-close is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 1,798 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.
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…