lld-gather

lld-gather is a skill for Claude Code from GoogilyBoogily/googilyboogily-claude-power-tools. It costs 53 tokens per session (1,715 once invoked), scanned A, original, MIT.

A tool that gathers and organizes the decisions, research, and constraints needed for a Low Level Design. It can also collect answers directly when no decision document exists.

In plain words
What is it for?
Use it to prepare a structured context file from architecture decisions, research, and a High Level Design (HLD), a broad description of a system's structure.
Why use it?
It fills gaps before detailed design work begins and labels assumptions instead of quietly inventing missing information.

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

Good fit Use it to prepare a structured context file from architecture decisions, research, and a High Level Design (HLD), a broad description of a system's structure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/googilyboogily/googilyboogily-claude-power-tools/lld-gather
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 lld-gather
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 lld-gather

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/lld-gather"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/lld-gather.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,715 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 $0.00053 $0.01715
Opus 5 $0.00026 $0.00857
Sonnet 5 $0.00011 $0.00343
Haiku 4.5 $0.00005 $0.00171

Measured 12d ago against content hash 88fbd1283174, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

lld-gather 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/lld-gather/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLD Context Gathering — Compiler Mode

Compile all context needed to write a Low Level Design document. In the full pipeline, this skill receives a decisions file (from lld-discuss), a research file (from arch-research), and an HLD reference, then merges them with gap-fill questions to produce the final context file.

Can also run standalone — if no decisions file is provided, falls back to direct Q&A mode.

Input

$ARGUMENTS — path to a decisions file or HLD, and optionally flags.

Parse for:

  • Decisions pathdocs/context/lld/<name>-decisions.md
  • HLD path--hld <path> or first arg if it looks like an HLD file path
  • Research path--research <path>
  • Description — if no files, treated as topic for standalone mode

Source Integrity Rules

Every factual claim in the context file must be traceable to research performed in this session.

  1. Cite your work. Reference specific file paths + line numbers.
  2. Never reference prior Claude sessions or Claude memory.
  3. Assumptions are labeled, not hidden.

Process

Human-in-the-loop: Never proceed past a decision point without user approval.

Mode Detection

Check if $ARGUMENTS points to a decisions file:

  • If YES → Compiler Mode (Phase 1-4)
  • If NO → Standalone Mode (Phase S1-S5)

Compiler Mode

Phase 1: Load Inputs

  1. Read the decisions file. Extract all D-XX decisions, HLD Constraints, Existing Code Patterns, Deferred Ideas, Open Questions.
  2. If --hld provided, read the HLD. Extract:
    • Component boundaries and responsibilities
    • API contracts and data models
    • Key design decisions and rationale
    • Implementation phases and dependencies
  3. If --research provided, read the RESEARCH.md. If not, check for <name>-RESEARCH.md.
  4. Scan docs/lld/ for existing LLDs.

Phase 2: Gap-Fill Questions

Compare decisions + research + HLD against LLD context needs:

Required Section Source Gap-Fill Needed?
Error Handling & Edge Cases Decisions file (D-XX on error handling) Ask for specific error codes if missing
State & Concurrency Decisions file Ask if stateful and not covered
Data Contracts Decisions + HLD API contracts Ask for exact types if missing
Integration Details Decisions + HLD external systems Ask for timeouts/retries if missing
Performance Constraints Decisions Ask for specific numbers if missing
Testing Strategy Decisions (D-XX on testing) Ask if approach unclear

Read the full file on GitHub · 224 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 · 224 lines · 53 tokens per session scan A 88fbd1283174

Subscribe to this mod's changes

lld-gather is a skill published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 1,715 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

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