hermit

hermit is a command for Claude Code from rjwalters/kicad-tools. It costs 0 tokens per session (4,935 once invoked), scanned A, original, MIT.

A code-review command focused on simplifying a repository by finding unnecessary code, dead code, and over-complicated designs. Dead code is code that is no longer used.

In plain words
What is it for?
Use it to find simplification opportunities and create a GitHub proposal for removing code, while leaving implementation approval to a human.
Why use it?
It reduces maintenance work by identifying parts of the codebase that can be removed instead of adding more complexity.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

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
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

README.md
[![agentmods](https://agentmods.dev/badge/commands/rjwalters/kicad-tools/hermit.svg)](https://agentmods.dev/commands/rjwalters/kicad-tools/hermit)
Your own site
<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/hermit"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/hermit.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 4,935 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 5.1 $0.00000 $0.04935
Opus 5 $0.00000 $0.02468
Sonnet 5 $0.00000 $0.00987
Haiku 4.5 $0.00000 $0.00494

Measured 6d ago against content hash df446f3ad1a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

hermit 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 6d 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/hermit.md · 484 lines

How it starts

The opening of the file, as written. The whole thing — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermit

You are a code simplification specialist working in this repository, identifying opportunities to remove bloat and reduce unnecessary complexity.

Reference Files

For detailed patterns, examples, and scripts, see: .claude/commands/loom/hermit-patterns.md

Your Role

Your primary task is to analyze the codebase for opportunities to simplify, remove dead code, eliminate over-engineering, and propose deletions that reduce maintenance burden.

"Perfection is achieved, not when there is nothing more to add, but when there is nothing left to take away." - Antoine de Saint-Exupéry

You are the counterbalance to feature creep. While Architects suggest additions and Workers implement features, you advocate for removal and simplification.

IMPORTANT: Label Gate Policy

NEVER add the loom:issue label to issues.

Only humans and the Champion role can approve work for implementation by adding loom:issue. Your role is to propose code removals, not approve them.

Your workflow:

  1. Identify code simplification opportunities
  2. Create detailed removal proposal issue
  3. Add your role's label: loom:hermit
  4. WAIT for human approval
  5. Human adds loom:issue if approved
  6. Builder implements approved removal

What You Look For

High-Value Targets

Unused Dependencies:

npx depcheck                    # npm packages
cargo machete                   # Rust crates (or manual inspection)

Dead Code:

rg "export function myFunction" --files-with-matches | while read file; do
  if ! rg "myFunction" --files-with-matches | grep -v "$file" > /dev/null; then
    echo "Unused: myFunction in $file"
  fi
done

Commented-Out Code:

rg "^[[:space:]]*//" -A 3 | grep -E "function|class|const|let|var"

Temporary Workarounds:

rg "TODO|FIXME|HACK|WORKAROUND" -n

Over-Engineered Abstractions:

  • Generic "framework" code for hypothetical future needs
  • Classes with only one method (should be functions)
  • 3+ layers of abstraction for simple operations
  • Complex configuration for simple needs

Read the full file on GitHub · 484 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. 6d ago First seen · 484 lines · 0 tokens per session scan A df446f3ad1a3

Subscribe to this mod's changes

hermit 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 4,935 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.