claude-code-methodology CLAUDE.md

claude-code-methodology CLAUDE.md is an instructions file for coding agents from cgmalone-ib/claude-code-methodology. It costs 1,626 tokens per session, scanned A, original, MIT.

Instructions for a methodology project about improving AI workflows, managing session continuity, and organizing reusable knowledge.

In plain words
What is it for?
Bootstrapping sessions, maintaining marker files, organizing examples and patterns, and developing workflow or productivity methods.
Why use it?
They keep work within the defined knowledge area and provide a process for preserving context when an AI session ends or reaches its limit.

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/cgmalone-ib/claude-code-methodology/claude-md
Clone the repo
git clone --depth 1 https://github.com/cgmalone-ib/claude-code-methodology

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 claude-code-methodology CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cgmalone-ib/claude-code-methodology/claude-md.svg)](https://agentmods.dev/instructions/cgmalone-ib/claude-code-methodology/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cgmalone-ib/claude-code-methodology/claude-md"><img src="https://agentmods.dev/badge/instructions/cgmalone-ib/claude-code-methodology/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,626 This file is loaded in full into every session.
When invoked 1,626 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 $0.01626 $0.01626
Opus 5 $0.00813 $0.00813
Sonnet 5 $0.00325 $0.00325
Haiku 4.5 $0.00163 $0.00163

Measured 4d ago against content hash 11cff990f0a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-methodology 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 4d 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 · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Session Bootstrap Instructions - Methodology Development

Core Expertise Declaration

You are an expert at AI workflow optimization, session management methodologies, token efficiency patterns, knowledge curation systems, and developer productivity tooling.

You do not jump the gun and make assertions unless they have been verified to be true.

I prefer discussing concepts before diving into implementation and only need generated artifacts/scripts when I ask for them.

Knowledge Space Structure

Knowledge Space: Restricted to specific directories within the current working directory:

  • Methodology Core: ./ - Root contains core methodology documents and templates
  • Examples: examples/ - Real-world implementation examples and case studies
  • Patterns: patterns/ - Reusable pattern library for common scenarios
  • Tools: tools/ - Helper scripts and automation tools

Do not venture into other directories outside this knowledge space, unless otherwise instructed.

Session Continuity Protocol

Purpose: Enable seamless work continuation when Claude sessions hit message limits.

Session Marker Files

  • Location: Knowledge space root directory (current working directory)
  • Format: .claude-session-methodology-{work-description}-{date}
  • Examples:
    • .claude-session-methodology-template-refinement-20250825
    • .claude-session-methodology-pattern-extraction-20250825
    • .claude-session-methodology-case-study-analysis-20250825

Bootstrap Program Loading Methodology

Paradigm: Load complete state first, then execute main() - not sequential script execution

Token Efficiency: Comprehensive loading prevents redundant operations and enables optimal decision-making Maintainability: Declarative state with explicit dependencies, change-resistant architecture

Program Loading Phase

Load ALL context before any execution decisions:

  1. Session State Loading

    # Load session markers
    glob .claude-session-*
    

Read the full file on GitHub · 241 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. 4d ago First seen · 241 lines · 1,626 tokens per session scan A 11cff990f0a0

Subscribe to this mod's changes

claude-code-methodology CLAUDE.md is an instructions file published in the GitHub repository cgmalone-ib/claude-code-methodology (2 stars, last pushed 1y ago), licensed MIT. It adds 1,626 tokens to every session, about $0.0081 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.