hermit-patterns

hermit-patterns is a command for Claude Code from rjwalters/kicad-tools. It costs 0 tokens per session (9,733 once invoked), scanned A, original, MIT.

Reference material with detailed examples and scripts for a Hermit role, including code-smell reviews, goal discovery, command syntax, and worktree cleanup.

In plain words
What is it for?
Use it when the main Hermit instructions point to a detailed review method, a discovery script, a command example, or cleanup guidance.
Why use it?
It gives the role concrete procedures for investigating code and handling repository tasks consistently.

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/hermit-patterns
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 hermit-patterns

README.md
[![agentmods](https://agentmods.dev/badge/commands/rjwalters/kicad-tools/hermit-patterns.svg)](https://agentmods.dev/commands/rjwalters/kicad-tools/hermit-patterns)
Your own site
<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/hermit-patterns"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/hermit-patterns.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 9,733 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.09733
Opus 5 $0.00000 $0.04866
Sonnet 5 $0.00000 $0.01947
Haiku 4.5 $0.00000 $0.00973

Measured 5d ago against content hash 5968259dbcff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hermit-patterns scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

return fetch(url).then(r => r.json());
.claude/commands/loom/hermit-patterns.md · 1,219 lines

How it starts

The opening of the file, as written. The whole thing — 1,219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermit Patterns Reference

This file contains detailed patterns, examples, and reference scripts for the Hermit role. It is meant to be consulted when needed, not loaded as primary instructions.

When to use this file:

  • Looking for specific code smell examples
  • Need detailed random file review workflow
  • Implementing goal discovery scripts
  • Checking command reference syntax
  • Need worktree cleanup implementation

Primary instructions: See hermit.md for core role definition and workflow.

Cached forge reads: the issue/PR listing commands below use the one documented helper $GH_READ instead of a raw gh issue list / gh pr list. It routes label/state list queries through loom-daemon's ETag-cached REST path (forge … list --cached, #5056) — a validated 304 is free and never stale — and falls back to plain gh when the daemon is unreachable or the shape is not cacheable (freeform --search, no --json). Resolve it once per session:

GH_READ="gh"
_ghc="$(git rev-parse --show-toplevel 2>/dev/null)/.loom/scripts/gh-cached"
if [[ -x "$_ghc" ]] && "$_ghc" --version >/dev/null 2>&1; then GH_READ="$_ghc"; fi

Full policy: .loom/docs/gh-cached.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.


Detailed Code Smell Examples

Look for these patterns that often indicate bloat:

1. Unnecessary Abstraction

// BAD: Over-abstracted
class DataFetcherFactory {
  createFetcher(): DataFetcher {
    return new ConcreteDataFetcher(new HttpClient());
  }
}

// GOOD: Direct and simple
async function fetchData(url: string): Promise<Data> {
  return fetch(url).then(r => r.json());
}

Read the full file on GitHub · 1,219 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. 5d ago First seen · 1,219 lines · 0 tokens per session scan A 5968259dbcff

Subscribe to this mod's changes

hermit-patterns is a command published in the GitHub repository rjwalters/kicad-tools (55 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 9,733 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.