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 pktikkani/agent-skills --skill design-canongit clone --depth 1 https://github.com/pktikkani/agent-skillsWrote 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/pktikkani/agent-skills/design-canon)<a href="https://agentmods.dev/skills/pktikkani/agent-skills/design-canon"><img src="https://agentmods.dev/badge/skills/pktikkani/agent-skills/design-canon/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/pktikkani/agent-skills/design-canon"><img src="https://agentmods.dev/badge/skills/pktikkani/agent-skills/design-canon.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 | $0.00063 | $0.00604 |
| Opus 5 | $0.00032 | $0.00302 |
| Sonnet 5 | $0.00013 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
design-canon 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 11d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design canon
The always-on core (~/Documents/design-best-practices.md) carries only the ten
convergent laws. This skill is for when a decision needs the full evidence, the
reasoning, or a specific engineer's profile.
How to use it
-
Read the full manual at
~/Documents/design-best-practices.md(~1,600 lines — the real manual). Do NOT rely on the distilled core alone for a non-trivial structural decision; the evidence and the anti-patterns are what make the directives actionable.Note: the manual itself is a personal document and is not bundled with this repo. This skill is the navigation contract for it — point it at your own design-principles document (any long-form manual works) by editing the path above.
-
Navigate, don't dump. Read the Meta-principles cheat-sheet first, then jump to the relevant profile/section for the decision at hand. Each principle is structured identically: principle → why it matters → concrete evidence → "As an agent, you should…" → the anti-pattern it corrects. The profiles:
- Profile 1 — Mitchell Hashimoto (Ghostty, HashiCorp, libxev): engineering discipline, simplest-correct-first, portable core / platform seam, comptime binding, one typed schema, config as public contract, data structures from access patterns, concurrency (owned config, typed messages, hot-path isolation).
- Profile 2 — Mario Zechner (libGDX, Pi harness): answer-first discipline, terse prose, read-to-blast-radius, deletion is confirmation-gated, machine-readable rules.
- Profile 3 — Armin Ronacher (Flask, Jinja2, Click, MiniJinja, insta).
- Profile 4 — Dax Raad (SST, opencode).
- Profile 5 — Simon Willison (Django, Datasette, sqlite-utils,
llm): leads with AI-Assisted Coding — supervise-don't-trust, context-is-king, close-the-loop, save-your-prompts. Read his Section A first if you read only one profile section.
-
Apply the relevant profile/section to the decision, cite the specific principle and its evidence when you justify a design choice, and run the manual's pre-flight checklist before finishing a non-trivial change.
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.
- 11d ago First seen · 42 lines · 63 tokens per session scan A f6436c842f80
design-canon is a skill published in the GitHub repository pktikkani/agent-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 604 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.
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…
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…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…