turnlens: Skill for Claude Code

.agents/skills/design-doc/SKILL.md

design-doc is a skill for Claude Code, Codex from kelesmert/turnlens. It costs 52 tokens per session (681 once invoked), scanned A, original, MIT.

A design-document workflow for changes that will be implemented in the same coding session. It records the problem, decisions, verified findings, constraints, tasks, files, interfaces, and required behaviours.

In plain words
What is it for?
Use it when designing a feature, refactor, or other code change that the same session will build.
Why use it?
It keeps the design and implementation aligned without creating a separate implementation plan for another worker. It also preserves the reasoning behind important technical choices.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is kelesmert/turnlens's own configuration. It tells Claude Code and Codex how to work on turnlens itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything turnlens configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/kelesmert/turnlens/main/.agents/skills/design-doc/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kelesmert/turnlens

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for design-doc

README.md
[![agentmods](https://agentmods.dev/badge/skills/kelesmert/turnlens/design-doc/github.svg)](https://agentmods.dev/skills/kelesmert/turnlens/design-doc)
Your own site
<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.

agentmods 80×15 button for design-doc

Your own site · 80×15
<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>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 681 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash 0b1ac45a5ae4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

.agents/skills/design-doc/SKILL.md · 63 lines

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.

Read the full file on GitHub · 63 lines

Changes

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.

  1. 10d ago First seen · 63 lines · 52 tokens per session scan A 0b1ac45a5ae4

Subscribe to this mod's changes

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.