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 vidhunnan/agentic-skills --skill design-decisionsgit clone --depth 1 https://github.com/vidhunnan/agentic-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/vidhunnan/agentic-skills/design-decisions)<a href="https://agentmods.dev/skills/vidhunnan/agentic-skills/design-decisions"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/design-decisions/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/vidhunnan/agentic-skills/design-decisions"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/design-decisions.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 | $0.00131 | $0.04882 |
| Opus 5 | $0.00066 | $0.02441 |
| Sonnet 5 | $0.00026 | $0.00976 |
| Haiku 4.5 | $0.00013 | $0.00488 |
Grade A, and why
design-decisions 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 12d 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 — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-decisions
Fills the design decisions tier — the folder that answers "why is it like this?" six months after everyone who knew has forgotten.
decisions-logger can mine a codebase, because code leaves evidence: commits,
diffs, PR threads, a config file that changed on a date. Design leaves none of
it. A Figma file shows the winner and nothing else — not the options, not the
reasoning, not the cost. So this skill inverts its sibling's design: there is almost
nothing to mine, and the evidence has to be captured from the person, in the
moment, or it will not exist at all.
That makes the fabrication risk worse here than anywhere else in this library. In code, an invented rationale can eventually be checked against a diff. A plausible reason for a layout choice is indistinguishable from a real one to every future reader, forever. There is nothing to check it against.
Three rules follow:
- Faithful, not generative. Every clause traces to a source or to the user's own
words.
*(reason not stated)*is a first-class outcome, not a failure — "we did this, nobody wrote down why" is exactly what a reader needs before they change it. - Name the loser or it isn't a decision. Design is a continuous stream of small choices. Without a hard gate this tier fills with noise and stops being read.
- Record the trade. Design choices are nearly always trades — legibility against density, speed against delight. The traded-away half is the first thing anyone asks about later and the first thing that decays into "that's just how it is." So What we gave up is a required section, not an optional one.
Instructions
Step 0 — Detect your surface
Using Bash availability:
- Claude Code — Bash works, real filesystem. Full flow.
- Claude.ai — no filesystem, no existing ADRs to compare against. Degrade: ask the user to paste their index (or say there isn't one), run the interview conversationally, emit each ADR as a downloadable artifact plus the index region and the CLAUDE.md block. Say plainly that dedup and supersession detection are unavailable here — do not guess at them.
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.
- 12d ago First seen · 384 lines · 131 tokens per session scan A 5df660154af8
design-decisions is a skill published in the GitHub repository vidhunnan/agentic-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 131 tokens to every session and 4,882 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
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…
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…