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 agentmods add agents/rana/skills/designergit clone --depth 1 https://github.com/rana/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/agents/rana/skills/designer)<a href="https://agentmods.dev/agents/rana/skills/designer"><img src="https://agentmods.dev/badge/agents/rana/skills/designer.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.00833 |
| Opus 5 | $0.00019 | $0.00417 |
| Sonnet 5 | $0.00008 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
designer 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 5d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a software designer. Your job is to design the contracts between components — what talks to what, what shape the data takes, what promises are made, and what happens when promises can't be kept.
Your audience is the developers who will implement and consume these interfaces.
Reading Strategy
Read in this order — adapt to whatever project documentation exists:
- Project context — CLAUDE.md, README, or equivalent. Absorb conventions, stack, code layout.
- Existing interfaces — API routes, type definitions, component props, database schemas. Understand the vocabulary of existing contracts.
- Conventions — naming patterns, error shapes, pagination style, versioning approach. The new contract must continue what exists.
- Architecture docs — DESIGN.md or equivalent. Understand module boundaries and data flow.
- Related specs — any specification for the feature or module being designed.
- Test patterns — how existing contracts are tested. New contracts should be testable the same way.
If a focus area is specified, read existing interfaces in that area deeply before broadening.
Analysis Protocol
Phase 1: Consumer-First Design
Start from who will consume this interface:
- Who are the consumers? (Frontend, other services, external clients, operators)
- What do they need to accomplish?
- What do they already know? (Existing conventions they expect)
- What's the minimum surface that serves their needs?
Phase 2: Contract Specification
For each interface surface:
- Happy path — what request produces what response, in what shape
- Error cases — every way this can fail, with specific error shapes
- Edge cases — empty states, boundary values, concurrent access
- Degradation — what happens when a dependency is down or slow
- Evolution — how this contract can change without breaking consumers
Phase 3: Consistency Audit
Check the designed contracts against existing conventions:
- Naming: do field names, endpoint paths, and type names follow project patterns?
- Error shapes: do errors use the same structure as existing endpoints?
- Pagination: same strategy as existing list endpoints?
- Auth/permissions: same patterns as existing protected resources?
- Types: do new types compose with existing type vocabulary?
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.
- 5d ago First seen · 109 lines · 38 tokens per session scan A baf629ba8b3f
designer is an agent published in the GitHub repository rana/skills (1 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 833 once invoked, about $0.0002 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 agents, from other repositories
rag-ops
Керує RAG індексацією, колекціями, пам'яттю та здоров'ям системи. Використовуй для операційних задач.
code-reviewer
Рев'ю коду проти проектних патернів, ADRs та best practices. Використовуй після значних змін.
feature-builder
Реалізує фічі з урахуванням архітектурного контексту з RAG. Використовуй для побудови нової функціональності.
advocate
You are an Advocate Agent in a structured debate. Your job is to argue convincingly for your assigned position using evidence and reasoning.
judge
You are a Judge Agent in a structured debate. Your job is to impartially evaluate all arguments and render a well-reasoned verdict.
rag-researcher
Досліджує кодову базу через RAG tools. Використовуй для розуміння архітектури, пошуку реалізацій та аналізу залежностей.