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 skills add hani-q/qstack --skill qstack-encode-lessons-in-structuregit clone --depth 1 https://github.com/hani-q/qstackWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hani-q/qstack/qstack-encode-lessons-in-structure)<a href="https://agentmods.dev/skills/hani-q/qstack/qstack-encode-lessons-in-structure"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-encode-lessons-in-structure/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hani-q/qstack/qstack-encode-lessons-in-structure"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-encode-lessons-in-structure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00054 | $0.00483 |
| Opus 5.5 | $0.00022 | $0.00193 |
| Sonnet 5.5 | $0.00011 | $0.00097 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
qstack-encode-lessons-in-structure 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 1mo 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.
What it actually says
Encode lessons in structure
Text asks every future reader to notice, remember, and comply. A structural mechanism applies the lesson without relying on memory.
Route the lesson
- Identify the concrete correction and evidence that it recurs. Keep a true one-off as local context instead of turning it into a universal rule.
- Choose the strongest practical mechanism:
- a state or type that cannot represent the invalid case;
- a schema, lint, banned API, or CI check that fails before merge;
- one canonical helper or generator that removes duplicate choices;
- a runtime boundary check with a clear failure;
- a written instruction only when human judgment is irreducible.
- Implement the mechanism only when the user's request authorizes that edit. Otherwise propose the exact target and expected failure behavior.
- Remove prose or duplicate paths that the new mechanism supersedes. Keep one source of truth, but only after proving the mechanism covers the old rule.
- Exercise the known failure and show that the mechanism catches it.
Route recurring fixes to a local skill or tool and systemic rules to the smallest shared layer that can enforce them. Recording a lesson without a mechanism that enforces it does not stop the next occurrence. Do not invent recurrence; cite the correction or failure that shows the pattern. Analysis alone does not authorize edits, commits, pushes, publishing, deployment, or external messages.
Adapted from Lauren Tan's PStack
principle-encode-lessons-in-structure
at commit 60c641e4fad674784b30abcf9f8915dea39df38d under the MIT License.
See third-party notices.
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.
- 1mo ago Changed · +1 lines 61bce02c225a
- 1mo ago First seen · 41 lines · 54 tokens per session scan A 4067564a0a4d
qstack-encode-lessons-in-structure is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 483 once invoked, about $0.0002 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…