builder-complexity

builder-complexity is a command for Claude Code from rjwalters/kicad-tools. It costs 0 tokens per session (5,382 once invoked), scanned A, original, MIT.

Guidance for judging the size and difficulty of software issues and splitting large issues into smaller pieces. It also defines what should happen when an agent cannot finish a claimed issue.

In plain words
What is it for?
Assessing issue complexity, breaking work into sub-issues, documenting blockers, and choosing between creating a pull request, decomposing the work, or marking it blocked.
Why use it?
It prevents complex work from being abandoned without an explanation or a next step. Smaller issues are easier to claim, implement, and review.

Command for Claude Code

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.

agentmods
npx agentmods add commands/rjwalters/kicad-tools/builder-complexity
Clone the repo
git clone --depth 1 https://github.com/rjwalters/kicad-tools

Made for: Claude Code.

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 builder-complexity

README.md
[![agentmods](https://agentmods.dev/badge/commands/rjwalters/kicad-tools/builder-complexity.svg)](https://agentmods.dev/commands/rjwalters/kicad-tools/builder-complexity)
Your own site
<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/builder-complexity"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/builder-complexity.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,382 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.05382
Opus 5 $0.00000 $0.02691
Sonnet 5 $0.00000 $0.01076
Haiku 4.5 $0.00000 $0.00538

Measured 3d ago against content hash e3273c720a4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

builder-complexity 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 3d 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.

.claude/commands/loom/builder-complexity.md · 559 lines

How it starts

The opening of the file, as written. The whole thing — 559 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Builder: Complexity Assessment and Issue Decomposition

This document covers complexity assessment, issue decomposition, and scope management for the Builder role. For the core builder workflow, see builder.md.

⚠️ --body @path Does NOT Expand — It Posts the Literal String

If you post a comment via gh issue comment / gh pr comment / gh api ... comments from a scratch file, --body @path (and gh api -f body=@path) posts the literal string @path, not the file's contents. Full pitfall, incident citation, and fixes: comment-body-literal-path.md.

Never Abandon Work

You must NEVER stop work on a claimed issue without creating a clear path forward.

When you claim an issue with loom:building, you are committing to ONE of these outcomes:

  1. Create a PR - Complete the work and submit for review
  2. Decompose into sub-issues - Break complex work into smaller, claimable issues
  3. Mark as blocked - Document the blocker and add loom:blocked label

NEVER do this:

  • Claim an issue, realize it's complex, then abandon it without explanation
  • Leave an issue with loom:building label but no PR and no sub-issues
  • Stop work because "it's too hard" without decomposing or documenting why

File issues with ./.loom/scripts/create-issue.sh, never a bare gh issue create (#5047). gh issue create is GraphQL-backed and dies outright once the shared GraphQL pool exhausts — while the independent REST pool sits ~99% unused. The script takes the same flags (--title, --body/--body-file, repeatable --label, --repo) and prints the same issue URL, but falls back to a single REST POST that applies labels atomically with creation. Recipe and rationale: .loom/docs/gh-issue-create-rest-fallback.md. (loom-daemon forge issue create is a byte-identical gh passthrough — NOT a fallback.) This matters most exactly here: a decomposition burst files 2-5 issues in a row, so it is the single likeliest place in a Builder run to meet an exhausted GraphQL pool mid-sequence.

Read the full file on GitHub · 559 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. 3d ago First seen · 559 lines · 0 tokens per session scan A e3273c720a4d

Subscribe to this mod's changes

builder-complexity is a command published in the GitHub repository rjwalters/kicad-tools (53 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,382 tokens. 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 2026-08-30.