agentmods.dev

arch-research

arch-research is a skill for Claude Code from GoogilyBoogily/googilyboogily-claude-power-tools. It costs 60 tokens per session (1,999 once invoked), scanned A, original, MIT.

A research phase for architecture decisions, where architecture means the structure and major technical choices of a system.

In plain words
What is it for?
Use it with a decisions file to produce a research document comparing options, citing code and web findings, and marking assumptions and confidence.
Why use it?
It turns decisions from an earlier discussion into focused research, with evidence and warnings about common implementation traps.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the architecture-docs plugin — 19 skills shipped together

not rated 2repo 4mo ago A scan 60 tokens original MIT

Good fit Use it with a decisions file to produce a research document comparing options, citing code and web findings, and marking assumptions and confidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/googilyboogily/googilyboogily-claude-power-tools/arch-research
View source ↗ GoogilyBoogily/googilyboogily-claude-power-tools
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 GoogilyBoogily/googilyboogily-claude-power-tools --skill arch-research
Clone the repo
git clone --depth 1 https://github.com/GoogilyBoogily/googilyboogily-claude-power-tools

Made for: Claude Code.

Or install architecture-docs, the plugin that ships this one along with the rest of its 19 skills.

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 arch-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/arch-research/github.svg)](https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/arch-research)
Your own site
<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/arch-research"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/arch-research/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.

agentmods 80×15 button for arch-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/arch-research"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/arch-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,999 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 $0.00060 $0.01999
Opus 5 $0.00030 $0.01000
Sonnet 5 $0.00012 $0.00400
Haiku 4.5 $0.00006 $0.00200

Measured 12d ago against content hash e22e6c683f84, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

arch-research 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 12d 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/architecture-docs/skills/arch-research/SKILL.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Research Phase

Investigate the technical implications of decisions captured during a discuss phase. This skill reads a decisions file, dispatches parallel code and web research focused on those specific decisions, merges findings, and produces a standalone RESEARCH.md.

Philosophy: Research should be guided by decisions, not generic. If the user decided "use Redis for caching" (D-03), research should investigate Redis patterns, pitfalls, and alternatives — not generic "caching best practices." The decisions file IS the research brief.

Input

$ARGUMENTS — path to a decisions file (from adr-discuss, hld-discuss, or lld-discuss).

If no path provided, check for recent decisions files:

  1. Glob docs/context/*/decisions/*-decisions.md
  2. Sort by modification time
  3. Present the most recent ones via AskUserQuestion

Source Integrity Rules

Every claim must trace to research performed in this session.

  1. Code findings cite file_path:line_number
  2. Web findings cite URLs with reliability ratings
  3. No references to prior Claude sessions or memory
  4. Assumptions explicitly labeled

Process

Phase 1: Parse Decisions & Plan Research

  1. Read the decisions file at $ARGUMENTS
  2. Extract:
    • All D-XX decisions (both User Decisions and Claude's Discretion)
    • Open Questions (these become primary research targets)
    • Prior Constraints (context for research scope)
    • Deferred Ideas (DO NOT research these — they're out of scope)
  3. Determine document type from file path:
    • docs/context/decisions/ → ADR research
    • docs/context/hld/ → HLD research
    • docs/context/lld/ → LLD research
  4. Plan research queries — for each D-XX decision and open question:
    • What needs code-level investigation? (existing patterns, gap analysis, reusable assets)
    • What needs web-level investigation? (best practices, library docs, known pitfalls)

Phase 2: Dispatch Parallel Research

Dispatch two Tasks in a single message (parallel execution):

Read the full file on GitHub · 223 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. 12d ago First seen · 223 lines · 60 tokens per session scan A e22e6c683f84

Subscribe to this mod's changes

arch-research is a skill published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 1,999 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.

PlanningResearch
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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens