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-prior-artnpx skills add hani-q/qstack --skill qstack-plan-prior-artgit 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 | $0.00148 | $0.03701 |
| Opus 5 | $0.00074 | $0.01851 |
| Sonnet 5 | $0.00030 | $0.00740 |
| Haiku 4.5 | $0.00015 | $0.00370 |
Grade A, and why
qstack-plan-prior-art 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qstack-plan-prior-art
Read the plans this project already wrote, then brief the plan about to be written. The corpus holds decisions that were made, work that was postponed on purpose, and execution records saying what the work actually cost.
This runs on its own, because the moment it helps is the moment nobody remembers to ask for it.
Read-only
Writes nothing into the plan folder. Never edits a plan, never appends to
board-events.js, never commits. The output is a brief in the response plus one
block the planner pastes into the new plan.
The brief is derived: delete it and a second run reproduces it. The durable part is the citations that land in the new plan's research-basis sheet. So keep the brief short and get the references exactly right.
The boundary with /qstack-reflect
/qstack-reflect counts. It reads across every worktree Git tracks, reports
numbers a reader can reproduce, and refuses to interpret them. A plan folder is
a file count there, never a source of meaning.
This skill reads the plan text and interprets it, for one purpose: informing the plan about to be written. That single purpose is what permits the interpretation. Do not widen it into a project health report, and do not fold the two skills together. Reflect stays mechanical, this one stays narrow.
Arguments
/qstack-plan-prior-art [plan-dir ...]
Every argument is a directory holding plans, relative to the repository root or
absolute. Supplied paths are authoritative: read those and skip discovery. This
is the escape hatch for a project whose plans live in docs/, in rfcs/, or
outside the repository.
The subject comes from the conversation rather than the arguments: it is the
feature the user is about to plan, or, when /qstack-plan-to-html is the
caller, whichever source that skill resolved: the Markdown draft, or the plan
summary the user just confirmed. When it is not clear, state what you took
it to be in the brief's first line, so a wrong guess is visible before anything
is read.
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.
- 2d ago First seen · 284 lines · 148 tokens per session scan A 4d8828b4482a
qstack-plan-prior-art is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 5d ago), licensed MIT. It adds 148 tokens to every session and 3,701 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
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
creating-skills
Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context…