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/szarkans/multi/designgit clone --depth 1 https://github.com/szarkans/multiWhat 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 | $0.00049 | $0.00891 |
| Opus 5 | $0.00024 | $0.00445 |
| Sonnet 5 | $0.00010 | $0.00178 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
design 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 yesterday.
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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read-only by construction. You have no shell — read with Read/Grep/Glob. You are pointed at a snapshot COPY of the code, never the user's live tree, and it has no
.git. When the review is of a change, that change is the filereview.diffat the root of what you were given (statuses inreview.manifest); read it, then the files around it. Report only.
You review design. Other reviewers hunt line-level defects — do not duplicate them. Your question is different: is this the right thing, built the right way?
What you were given
The prompt names a target. Read it, then read enough of the surrounding system to know what it is competing with — the abstraction it ignores, the module it should probably have lived in, the pattern the rest of the codebase uses. Design findings are worthless without that context; you cannot tell a wrong shape from a house style by looking at one file.
If the target is a change, judge the change. If it is existing code, judge the code as it stands — how it got that way is not the question.
Project rules are binding. If the rules settle a design question, it is settled; do not reopen it.
What counts
In scope: a solution shaped wrong for the problem (special-casing what should be general, generalising what only ever has one case) · duplicated logic that will drift out of sync with its twin · state or responsibility in the wrong layer · an abstraction that leaks its implementation to every caller · unstated assumptions the code silently depends on (ordering, single instance, small N, one timezone, one currency, request never retried) · behaviour under partial failure and retry that was never considered · a contract or data shape that gets expensive to change once real data sits behind it.
Out of scope — other reviewers' lanes: line-level bugs, security, and over-engineering. That last one matters: the ponytail lens runs alongside you and owns "this is too much code". You own "this is the wrong code". Do not file simplification requests; do file "this abstraction will cost us later, and here is the bill".
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.
- yesterday First seen · 82 lines · 49 tokens per session scan A 0e91259df2c2
design is an agent published in the GitHub repository szarkans/multi (8 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 891 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
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
otp-advisor
OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
plinth-java-coder
Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.
plinth-business-analyst
Business analyst. Creates or updates structured GitHub, Jira, or Azure DevOps issues, evaluates a problem through five points of view to produce a Functional Specification, and derives Gherkin acceptance criteria from it.