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 w2ur/claude-code-setup --skill design-tellsgit clone --depth 1 https://github.com/w2ur/claude-code-setupWrote 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/w2ur/claude-code-setup/design-tells)<a href="https://agentmods.dev/skills/w2ur/claude-code-setup/design-tells"><img src="https://agentmods.dev/badge/skills/w2ur/claude-code-setup/design-tells/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/w2ur/claude-code-setup/design-tells"><img src="https://agentmods.dev/badge/skills/w2ur/claude-code-setup/design-tells.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 | $0.00019 | $0.04133 |
| Opus 5.5 | $0.00008 | $0.01653 |
| Sonnet 5.5 | $0.00004 | $0.00827 |
| Haiku 4.5 | $0.00002 | $0.00413 |
Grade A, and why
design-tells 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 6d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design tells — the patterns that read as model-generated
The short rule lives in ~/.claude/CLAUDE.md (Design defaults). This skill holds
the full trap list behind it, each pattern with why it reads as a model
default and what to do instead.
Why a named list and not "avoid the AI look". Without a direction, Opus 5.5 falls back on a few default styles. A generic "avoid the AI look" only swaps one default for another; naming the pattern is what works.
Source: the three research strands of workflow wf_10b4186b-05c (2026-09-18, the
hub's the-portfolio redesign): A state of the art, B a site without
images, C what the visitor actually needs. The A0-style ids point back to
.result.recherches[<strand>].pieges[<n>] in that run; a row carrying several ids
(A7 · B10 · C6) is one pattern the strands found independently. G-ids are
rules drawn from the Opus 5.5 migration guide, not from that run. R-ids
(section 4) come from other design skills, each row tagged with its source.
The detector column names the Impeccable rule id that catches the row's
detectable part (pinned CLI, run through ~/.claude/scripts/design-detect.sh);
— means judgment only. A hit is evidence, not a verdict: design-critique
reads it and decides which hits a documented identity sanctions.
The carve-out: a documented identity overrides this list
A project whose own CLAUDE.md has a design section (palette, type, motifs), or
that has a DESIGN.md at its root, has a direction, and that document wins
over every entry below. The hub
({portfolio-site}) is the reference case: its cream paper ground, serif and
handwritten notes are a deliberate, documented identity, not a default to remove.
Without such a document, a cream or off-white ground is the tell on its own (G1), whatever accent and type come with it. Only a documented identity makes it legitimate, and even then what still applies is the companions (A0): cream plus an italic accent word plus a terracotta accent plus numbered eyebrows. Keep the identity, refuse the companions it did not ask for.
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.
- 6d ago Changed · +26 lines 6ab82f6b6f5f
- 21d ago First seen · 99 lines · 19 tokens per session scan A df0447697214
design-tells is a skill published in the GitHub repository w2ur/claude-code-setup (2 stars, last pushed 3d ago), licensed MIT. It adds 19 tokens to every session and 4,133 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.