Borrowing it
Nothing to install: this file belongs to gotgenes/pi-anthropic-auth. 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/gotgenes/pi-anthropic-auth/main/.pi/skills/design-review/SKILL.mdgit clone --depth 1 https://github.com/gotgenes/pi-anthropic-authWrote 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/gotgenes/pi-anthropic-auth/design-review)<a href="https://agentmods.dev/skills/gotgenes/pi-anthropic-auth/design-review"><img src="https://agentmods.dev/badge/skills/gotgenes/pi-anthropic-auth/design-review/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/gotgenes/pi-anthropic-auth/design-review"><img src="https://agentmods.dev/badge/skills/gotgenes/pi-anthropic-auth/design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.01351 |
| Opus 5.5 | $0.00016 | $0.00540 |
| Sonnet 5.5 | $0.00008 | $0.00270 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
design-review 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 1mo 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Review
Use this skill to audit a module (or a set of related modules) for structural smells before they accumulate into a large refactoring.
When to invoke
- A shared interface (options bag, config type, handler params) is gaining a new field.
- A test factory helper has more than 8 fields.
- A plan adds a parameter that threads through 3+ layers.
- A change reads as a localized bug fix but adds or relays a parameter across functions — a bug fix can be a wiring change.
- You are unsure whether a new dependency belongs on an existing object or needs a new one.
- The same comparison (
platform === "win32",status === "running") appears at 3+ sites across modules.
Checklist
Work through each check in order.
Use grep and read to gather evidence before making judgments.
1. Dependency width
Grep for the interface or type being reviewed. Count the fields. For each consumer (function or class that receives it), list which fields that consumer actually reads or writes.
Ask:
- Does every consumer use more than half the fields? If not, the interface is too wide.
- Are there natural clusters of fields that always appear together? Those are missing intermediate abstractions (value objects or collaborator interfaces).
Also flag projection parameters: when a function receives both X and Y and X is derivable from Y (a field or parse-product of it), drop X and read it from Y — the object that owns the data.
Example: passing a raw command string alongside a parsed program object built from that command; give the parsed object a commandText() accessor instead.
2. Law of Demeter violations
Search for chained access patterns (e.g., deps.foo.bar.baz).
Each chain a.b.c() means a exposes b and the caller talks to b directly — a coupling that leaks into tests.
The fix is a method on a that delegates to b internally.
Ask:
- Do multiple callers perform the same reach-through? That confirms the missing method.
- Does the intermediate object appear in the caller's test mocks? If yes, the coupling is leaking into tests.
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.
- 1mo ago Changed · -1 lines · -8 tokens per session b5ba5218aee8
- 2mo ago First seen · 135 lines · 47 tokens per session scan A 98e77c318b27
design-review is a skill published in the GitHub repository gotgenes/pi-anthropic-auth (426 stars, last pushed 13d ago), licensed MIT. It adds 39 tokens to every session and 1,351 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
prose-review
Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…
text-search
Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.
pixiv-cli-pr
Prepare, update, or verify a pixiv-cli pull request using its current template, trusted verification policy, reviewed diff, and head-specific check results. Use for contributor handoff or PR readiness; merging, live /test execution, and releases are separate actions.
claude-md-improver
Audit and improve existing CLAUDE.md files across a repository. Use for a deliberate, repo-wide quality review—not to record learnings from the current session.
review-harness
Use when reviewing implementation work that ran through a /tmp Pi task harness. Checks contract drift, unsafe shortcuts, validation evidence, and status honesty.
claude-md-revision
Record durable, project-specific learnings from the current session in CLAUDE.md, .claude.local.md, or AGENTS.md—not general documentation, session summaries, or repo-wide audits.