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-reflectnpx skills add hani-q/qstack --skill qstack-reflectgit 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 | $0.00132 | $0.06446 |
| Opus 5 | $0.00066 | $0.03223 |
| Sonnet 5 | $0.00026 | $0.01289 |
| Haiku 4.5 | $0.00013 | $0.00645 |
Grade A, and why
qstack-reflect 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 — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qstack-reflect
Report how this project is being worked, using only facts that can be counted and re-checked. Read-only: never edit tracked files, never commit, never change a branch or working tree.
This is a mechanical evidence pass. Do not interpret motive, diagnose the reader, or write anything you cannot cite a number for. A finding is a count plus its location. If a category lacks evidence, say so and move on.
Arguments
/qstack-reflect [plan-dir ...]
Every argument is a directory holding plan documents, relative to the
repository root or absolute. Supplied paths are authoritative: use exactly
those and skip plan discovery entirely. This is the escape hatch for any
project whose plans live somewhere this skill would not think to look: a
docs/ tree, an rfcs/ directory, a path outside the repository.
With no arguments, fall back to discovery (category E). Discovery is a convenience for projects using a known layout, not a claim to know where a given project keeps its plans. When it finds nothing, say where it looked and name this argument, rather than concluding the project has no plans.
Scope
- Resolve the repository root with
git rev-parse --show-toplevel. Outside Git, say the skill needs a Git repository and stop. - Take the checkout set from
git worktree list --porcelain. Git maintains this list itself, so it is an answer rather than a guess: no directory convention to match, no candidate to verify, and nothing to exclude. - State the scope out loud before any finding: repository, how many checkouts,
how many of those Git marks
prunable, and the commit span.
Do not enumerate directories looking for sibling checkouts, and do not compare remote URLs to decide which belong. An earlier version did both. It missed checkouts living outside the directory convention it knew: nine against five on the first project it ran against: while the URL comparison it needed to screen out strangers had to reason about protocols, ports and absent remotes, none of which it got right. Git already knows where its worktrees are.
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 · 520 lines · 132 tokens per session scan A c17bd4a9ba02
qstack-reflect is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 5d ago), licensed MIT. It adds 132 tokens to every session and 6,446 once invoked, about $0.0007 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
nemoclaw-contributor-implement-issue
Implement an accepted NemoClaw GitHub issue in the current checkout. Use when a user asks to pick up an issue for implementation, implement or fix a named issue, or add the issue's tests. Confirm accepted scope, deliver the smallest independently valuable capability slice, and record validation and remaining gates…
amazon-bestseller-listing
Amazon Best Sellers listing scraper: extract product cards from any Amazon Best Sellers (zgbs) or /gp/bestsellers/ category page — returns rank (position on chart), asin, title, url, image, imageAlt, price, stars, reviewCount, ratingRaw per item, plus category metadata (categoryName, categoryFullName, categoryUrl) and…
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
cabloy-worktree-environment
This skill must be used only when the user explicitly invokes /cabloy-worktree-environment or explicitly asks to perform the named Cabloy worktree-environment setup. It prepares a confirmation-gated, worktree-local Vona and Zova runtime environment for a linked Cabloy Basic or Cabloy Start Git worktree using Git…
shopify-hydrogen
Hydrogen storefront implementation cookbooks. Some of the available recipes are: B2B Commerce, Bundles, Combined Listings, Custom Cart Method, Dynamic Content with Metaobjects, Express Server, Google Tag Manager Integration, Infinite Scroll, Legacy Customer Account Flow, Markets, Partytown + Google Tag Manager…