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 shaharsha/claude-skills --skill tech-design-docgit clone --depth 1 https://github.com/shaharsha/claude-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/shaharsha/claude-skills/tech-design-doc)<a href="https://agentmods.dev/skills/shaharsha/claude-skills/tech-design-doc"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/tech-design-doc/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/shaharsha/claude-skills/tech-design-doc"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/tech-design-doc.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 | $0.00113 | $0.01707 |
| Opus 5 | $0.00056 | $0.00853 |
| Sonnet 5 | $0.00023 | $0.00341 |
| Haiku 4.5 | $0.00011 | $0.00171 |
Grade A, and why
tech-design-doc 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Design Doc
The only thing a design doc optimizes for is decision quality — can a reasonable reviewer make the right call from this doc in one meeting. Most "bad" design docs aren't bad at writing; they're bad at triage. Get the format right and 70% of the work is done.
Triage first (do this every time)
Q1. Recording a decision already made, OR seeking buy-in?
└─ recording → ADR (~1 page)
Q2. Buy-in: how many stakeholders?
├─ 1-3 your team → standard RFC (4-6 pages, 60-min review)
├─ 4-10 cross-team → standard RFC + formal approvers list
└─ org-spanning / infra → heavyweight (10-20 pages, KEP + PRR)
Q3. Audience is an external partner (different company)?
└─ yes → switch to partner-mode (adds glossary, ownership table, "proposing" tone)
Default if unsure: standard RFC. Need evidence to grow heavyweight or shrink to ADR.
Edge cases (PR/FAQ vs design doc, splitting, when ADR should grow into RFC) → reference/triage.md.
Templates
| Template | Pages | Meeting | When |
|---|---|---|---|
mini-adr.md.tmpl |
1-2 | 30 min or async | Decision already made — recording it. Nygard format. |
standard-rfc.md.tmpl |
4-6 | 60 min | Buy-in for a non-trivial design, one team. Rust-RFC skeleton. |
heavyweight-doc.md.tmpl |
10-20 | multi-week | Org-spanning, infra-sensitive. KEP + Production Readiness Review. |
partner-doc.md.tmpl |
flexible | varies | External dev partner. Standard + glossary + ownership table. |
Workflow
1. Triage → pick template
2. Scaffold → scripts/new-doc.sh --template <t> --slug <s> --title "..."
3. Outline (BLUF) → Summary + Goals/Non-Goals first
4. Alternatives → ≥3 alternatives BEFORE detailing the proposal
5. Design → proposal + diagrams (C4 context + sequence)
6. Cross-cutting → fill checklist; mark N/A explicitly with reason
7. Audit → scripts/audit-doc.py <file>
8. Pre-read → distribute 24h before meeting (48h for partner-mode)
9. Decide → meeting (or async) → status flips
10. Log → scripts/append-decision-log.py → row in DECISIONS.md
11. (optional) Sync → gdoc-sync to a live Doc
What ships with it
20 files 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.
- .gitignore 29 B
- README.md 7.8 KB
- reference/alternatives-considered.md 5.3 KB
- reference/anti-patterns.md 7.5 KB
- reference/canonical-outline.md 7.7 KB
- reference/cross-cutting-checklist.md 5.2 KB
- reference/diagrams.md 6.6 KB
- reference/examples/mini-adr-example.md 2.3 KB
- reference/examples/standard-rfc-example.md 9.7 KB
- reference/meeting-protocol.md 6.0 KB
- reference/non-goals.md 4.0 KB
- reference/partner-mode.md 7.2 KB
- reference/triage.md 5.2 KB
- scripts/append-decision-log.py 3.5 KB runs code
- scripts/audit-doc.py 19 KB runs code
- scripts/new-doc.sh 3.8 KB runs code
- templates/heavyweight-doc.md.tmpl 5.1 KB
- templates/mini-adr.md.tmpl 1.2 KB
- templates/partner-doc.md.tmpl 4.4 KB
- templates/standard-rfc.md.tmpl 4.9 KB
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 · 106 lines · 113 tokens per session scan A fb0569f3de49
tech-design-doc is a skill published in the GitHub repository shaharsha/claude-skills (5 stars, last pushed 13d ago), licensed MIT. It adds 113 tokens to every session and 1,707 once invoked, about $0.0006 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…