Borrowing it
Nothing to install: this file belongs to kelesmert/turnlens. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kelesmert/turnlens/main/.agents/skills/design-doc/SKILL.mdgit clone --depth 1 https://github.com/kelesmert/turnlensWrote 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/kelesmert/turnlens/design-doc)<a href="https://agentmods.dev/skills/kelesmert/turnlens/design-doc"><img src="https://agentmods.dev/badge/skills/kelesmert/turnlens/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/kelesmert/turnlens/design-doc"><img src="https://agentmods.dev/badge/skills/kelesmert/turnlens/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 | $0.00052 | $0.00681 |
| Opus 5 | $0.00026 | $0.00341 |
| Sonnet 5 | $0.00010 | $0.00136 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
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 10d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design documents for inline work
When the work will be done inline, superpowers:brainstorming writes one
document and superpowers:writing-plans is not invoked afterwards. The
document goes to docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md. Nothing
is written to docs/superpowers/plans/.
Why one document
The plan format carries working code because a fresh subagent sees only its own task and cannot ask a question. Inline there is no such reader: the session that designs the work also implements it. The code is then written twice -- once unverified in the plan, once again while implementing. Plans 1 through 3 spent 8,439 lines that way to produce 7,557 lines of source and tests.
What the document contains
Everything a spec had -- problem, decisions with their reasoning, verified findings, out of scope -- plus the parts of a plan that survive inline:
- Global constraints, copied verbatim, so no task re-decides them.
- Tasks in order, each ending in a commit. Per task: the deliverable, the files to create or modify, the interface it produces as signatures only, which existing code to reuse rather than rewrite, the behaviours that must hold and therefore be tested, and the command that proves it together with its expected output.
- A self-review of the finished document: spec coverage, placeholders, and type consistency between tasks.
No implementation bodies and no pre-written test bodies. Both are unverified code, and TDD derives an implementation from its test rather than from a document.
The shape to aim for is around 350 lines for a plan-sized piece of work: type
signatures and interface blocks where an interface is being fixed, and
everything else as prose. If a section could be pasted into a source file and
compile, it is too much. The two design documents written to this rule came to
460 and 532 lines and replaced plans that would have run to thousands.
One gate, not two
One document means one review gate where there were two. Present the design in sections and take approval as you go, so the written file records a design already agreed rather than being the first sight of it.
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.
- 10d ago First seen · 63 lines · 52 tokens per session scan A 0b1ac45a5ae4
design-doc is a skill published in the GitHub repository kelesmert/turnlens (2 stars, last pushed 28d ago), licensed MIT. It adds 52 tokens to every session and 681 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
grant-proposal-builder
Nonprofit and research grant proposal assembly with structured sections, budget templates, and evaluation alignment. Use when writing grant proposals, funding applications, or research funding requests.
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
audio-production
Professional audio production for music, podcasts, and sound design. Use when working with audio recording, mixing, mastering, or sound design for any medium.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.