trove-architect

trove-architect is a skill for Claude Code from bravew/trove. It costs 59 tokens per session (562 once invoked), scanned A, original, MIT.

A workflow for planning the structure of non-trivial code before implementing it, using types, function signatures, and module boundaries with unfinished bodies.

In plain words
What is it for?
Use it to understand existing code, sketch a design, optionally get agreement on risky choices, then fill in the implementation.
Why use it?
It helps expose poor data shapes and module boundaries before substantial code has been written.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

Part of the trove-dev plugin — 15 skills, 1 agent shipped together

Good fit Use it to understand existing code, sketch a design, optionally get agreement on risky choices, then fill in the implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bravew/trove/trove-architect
View source ↗ bravew/trove
Install

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.

Any agent
npx skills add bravew/trove --skill trove-architect
Clone the repo
git clone --depth 1 https://github.com/bravew/trove

Made for: Claude Code.

Or install trove-dev, the plugin that ships this one along with the rest of its 15 skills, 1 agent.

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 trove-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/bravew/trove/trove-architect.svg)](https://agentmods.dev/skills/bravew/trove/trove-architect)
Your own site
<a href="https://agentmods.dev/skills/bravew/trove/trove-architect"><img src="https://agentmods.dev/badge/skills/bravew/trove/trove-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 562 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 $0.00059 $0.00562
Opus 5 $0.00030 $0.00281
Sonnet 5 $0.00012 $0.00112
Haiku 4.5 $0.00006 $0.00056

Measured 8d ago against content hash f50a83fdbb1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

trove-architect 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 8d 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.

plugins/trove-dev/.agents/skills/trove-architect/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trove · v2026.7.4

Session Init

This skill ships Trove conventions. Prefer existing project patterns over generic best practices when they conflict.

If a sibling skill in this plugin matches the request more directly, defer to it. See AGENTS.md (or docs/routing.md in the marketplace) for the per-plugin routing index.

trove-architect

Design the shape before writing the code. The shape is the types, the signatures, and the module boundaries — with not implemented bodies. Get the data shape right first (trove-principle-data-shape) and make it honest (trove-principle-type-discipline).

Phases

  1. Ground. Understand the existing code via trove-explain (read the real code, don't guess). Skip for greenfield.
  2. Sketch. Write the types, function signatures, and module map with stubbed (throw new Error('not implemented')) bodies. This is the artifact to review — it's cheap to change now.
  3. Agree (optional gate). For contested or high-blast-radius shapes, confirm the sketch before filling in. For routine work, proceed.
  4. Implement. Fill in the bodies. Ship the synthesis (the sketch) as its own commit so later commits read as filling in bodies.
  5. Scrap when wrong. Watch for the tells that the shape is wrong and rewrite the sketch rather than forcing it.

Scrap tells

Rewrite the shape — don't paper over it — when you see a pattern (not a single case) of:

  • The same workaround repeated to fit the types.
  • Escape hatches creeping in (any, casts, optional fields that "shouldn't" be optional).
  • The "we need a lock / a flag / a side channel" reflex to make the shape work.

One awkward spot is normal. A pattern of them means the foundation is wrong; redesign as if you'd known on day one.

Anti-patterns

  • Don't sketch a trivial one-liner — that's over-process. This is for work where the wrong shape is expensive.
  • Don't keep filling in a sketch that keeps fighting you. Scrapping early is cheaper than a built-out wrong shape.

Read the full file on GitHub · 42 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. 8d ago First seen · 42 lines · 59 tokens per session scan A f50a83fdbb1a

Subscribe to this mod's changes

trove-architect is a skill published in the GitHub repository bravew/trove (10 stars, last pushed 9d ago), licensed MIT. It adds 59 tokens to every session and 562 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens