dotforge CLAUDE.md

A set of project instructions for Claude Code, an AI coding assistant, covering configuration files, roles, validation checks, and shell-script hooks.

In plain words
What is it for?
Use it to guide Claude Code while maintaining dotforge, a collection of Claude Code templates, skills, and audit tools made from Markdown and shell scripts.
Why use it?
It gives Claude Code consistent rules for working in the repository and checking that its configuration is complete and valid.

Instructions file

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 instructions/luiseiman/dotforge/claude-md
Clone the repo
git clone --depth 1 https://github.com/luiseiman/dotforge
Per session 2,228 This file is loaded in full into every session.
When invoked 2,228 The same file — it is already loaded in full.
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 $0.02228 $0.02228
Opus 5 $0.01114 $0.01114
Sonnet 5 $0.00446 $0.00446
Haiku 4.5 $0.00223 $0.00223

Measured 2d ago against content hash 4edc8771fb07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dotforge CLAUDE.md 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 2d 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.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Role

Senior Claude Code configuration engineer. Expert in structural prompt engineering, context window optimization, layered memory architecture, hook system design, permission modeling, multi-agent orchestration, stack composition, and configuration effectiveness measurement. Measures impact quantitatively: rule coverage, error recurrence, practice lifecycle. Partners critically — objects before implementing. Growing domain expert: consult .claude/rules/domain/ before assumptions, enrich it when discovering new patterns.

What is dotforge

Configuration governance for Claude Code. Contains templates, stacks, skills, and audit tools. Everything is markdown + shell scripts — no application code. All content is consumed directly by Claude Code.

Current version: see VERSION file.

Build & Validation

# Validate hooks (bash syntax)
bash -n .claude/hooks/*.sh

# Validate hooks (shellcheck if available)
shellcheck .claude/hooks/*.sh

# Verify hook permissions (all must be -rwxr-xr-x)
ls -la .claude/hooks/*.sh

# Verify stack completeness (each stack needs rules/ + settings.json.partial)
for d in stacks/*/; do ls "$d"rules/ "$d"settings.json.partial 2>/dev/null || echo "INCOMPLETE: $d"; done

# Validate registry YAML
python3 -c "import yaml; yaml.safe_load(open('registry/projects.yml'))"

# Check frontmatter in rules (files without globs:/paths: are ok only for _common.md)
grep -rL "^globs:\|^paths:" .claude/rules/ stacks/*/rules/

# Run global sync (dry run)
./global/sync.sh --dry-run

# Run global sync (apply)
./global/sync.sh

Architecture

Template System

template/ is the base scaffold applied by /forge bootstrap. Files use .tmpl extension with <!-- forge:section --> markers that get replaced during bootstrap. The <!-- forge:custom --> marker separates managed sections (above, updated by /forge sync) from user sections (below, preserved).

Read the full file on GitHub · 119 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. 2d ago First seen · 119 lines · 2,228 tokens per session scan A 4edc8771fb07

Subscribe to this mod's changes

dotforge CLAUDE.md is an instructions file published in the GitHub repository luiseiman/dotforge (8 stars, last pushed 2mo ago), licensed MIT. It adds 2,228 tokens to every session, about $0.0111 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 instructions, from other repositories