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-to-htmlnpx skills add hani-q/qstack --skill qstack-plan-to-htmlgit 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 | $0.00068 | $0.07124 |
| Opus 5 | $0.00034 | $0.03562 |
| Sonnet 5 | $0.00014 | $0.01425 |
| Haiku 4.5 | $0.00007 | $0.00712 |
Grade A, and why
qstack-plan-to-html 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 — 608 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qstack-plan-to-html
Takes a plan, from a Markdown draft or from the conversation that worked it out, and produces a controlled document: numbered, citable, offline-safe, and readable by two audiences at once.
A plan is not a landing page. It opens with a title block, every clause is numbered so a reviewer can say "§4.2 is wrong", and every section carries a status stamp so a reader knows what is settled before reading a word.
Language: plain words, always
Write it the way you would say it out loud. Jargon is not precision; most of the time it is precision's opposite, because it lets a vague sentence pass as an informed one. If a sentence would survive being read aloud to a smart person outside the team, keep it. If it would not, rewrite it.
Cut these on sight: they carry no information:
leverage · utilize · synergy · holistic · robust · seamless · paradigm · best-in-class · surface area (as a metaphor) · first-class citizen · orthogonal · non-trivial · trivially · simply · just · obviously
| Instead of | Write |
|---|---|
| "leverage the existing abstraction" | "use the code that is already there" |
| "a non-trivial refactor" | "about three days of work across four files" |
| "the system exhibits sub-optimal latency characteristics" | "it takes 40 seconds; it should take 2" |
| "we surface this to the operator" | "the operator sees it" |
| "simply add a policy rule" | "add a policy rule": if it were simple you would not be writing a plan |
Precise is not the same as jargon. A term of art that names a real thing in
A term already used in the codebase, such as first-match, hot reload, or
run-to-completion, stays because
replacing it with a vague paraphrase loses information an implementer needs. The
rule is: use the exact word, then explain it once in an ELI10 box the first
time it appears.
Numbers beat adjectives. "Fast" is an opinion; "16 ms" is a fact. Wherever the source markdown has a measurement, use the measurement.
What ships with it
20 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.
- agents/openai.yaml 262 B
- references/board-breakdown.md 15 KB
- references/board-protocol.md 25 KB
- template/migrate-board-log 2.4 KB
- template/serve.sh 663 B runs code
- template/v1/board.js 27 KB runs code
- template/v1/fonts/archivo-var.woff2 34 KB
- template/v1/fonts/OFL-Archivo.txt 4.3 KB
- template/v1/fonts/OFL-IBMPlexMono.txt 4.4 KB
- template/v1/fonts/OFL-SourceSerif4.txt 4.3 KB
- template/v1/fonts/plexmono-400.woff2 9.8 KB
- template/v1/fonts/plexmono-500.woff2 9.8 KB
- template/v1/fonts/README.md 1.6 KB
- template/v1/fonts/sourceserif4-italic-var.woff2 127 KB
- template/v1/fonts/sourceserif4-var.woff2 119 KB
- template/v1/plan-template.html 9.3 KB
- template/v1/plan.css 39 KB
- template/v1/plan.js 9.8 KB runs code
- template/v1/pretext.js 30 KB runs code
- template/v1/README.md 16 KB
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 · 608 lines · 68 tokens per session scan A eeb88001e0b6
qstack-plan-to-html is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 5d ago), licensed MIT. It adds 68 tokens to every session and 7,124 once invoked, about $0.0003 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…