Ladder: Instructions file for Claude Code

CLAUDE.md

Ladder CLAUDE.md is an instructions file for Claude Code from danielmiessler/Ladder. It costs 424 tokens per session, scanned A, original, MIT.

Repository guidance for Ladder, an open-source system that turns sources into ideas, testable hypotheses, experiments, and results. It stores each item as Markdown with metadata and linked identifiers.

In plain words
What is it for?
It helps agents add and link research entries, use the required statuses and identifiers, navigate the repository folders, and run the project’s Bun-based command-line tool.
Why use it?
It keeps research records organized and traceable from an original source through testing and verified results.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is danielmiessler/Ladder's own configuration. It tells Claude Code how to work on Ladder itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Ladder configures →

Reuse

Borrowing it

Nothing to install: this file belongs to danielmiessler/Ladder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/danielmiessler/Ladder/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/danielmiessler/Ladder

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 Ladder CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/danielmiessler/ladder/claude-md/github.svg)](https://agentmods.dev/instructions/danielmiessler/ladder/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/danielmiessler/ladder/claude-md"><img src="https://agentmods.dev/badge/instructions/danielmiessler/ladder/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Ladder CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/danielmiessler/ladder/claude-md"><img src="https://agentmods.dev/badge/instructions/danielmiessler/ladder/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 424 This file is loaded in full into every session.
When invoked 424 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00424 $0.00424
Opus 5.5 $0.00170 $0.00170
Sonnet 5.5 $0.00085 $0.00085
Haiku 4.5 $0.00042 $0.00042

Measured 2mo ago against content hash 39639a7bce4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Ladder 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 2mo 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 · 49 lines

What it actually says

Ladder — AI Guidance

What Is This?

Ladder is an open source pipeline for systematic improvement: Sources → Ideas → Hypotheses → Experiments → Results, with results feeding back as sources (the loop).

Key Conventions

  • IDs: Each collection uses a prefix: SR-, ID-, HY-, EX-, AL-, RE- followed by 5-digit zero-padded number
  • Format: All entries are markdown with YAML frontmatter
  • Status values: draft, active, testing, complete, archived
  • Linking: Entries reference upstream items (e.g., a hypothesis links to its parent idea via idea: ID-00001)
  • CLI: Use bun run ladder <command> — never npm/npx

Directory Structure

  • Sources/ — Raw inputs (papers, articles, observations, telemetry)
  • Ideas/ — Candidate solutions generated from sources
  • Hypotheses/ — Testable predictions from ideas
  • Experiments/ — Structured tests with methodology
  • Algorithms/ — Proven methods for specific tasks
  • Results/ — Verified outcomes from experiments
  • Tools/ — TypeScript CLI tooling (bun-based)

When Adding Entries

  1. Use the CLI: bun run ladder add <type> --title "..."
  2. Or create manually following the TEMPLATE.md in each directory
  3. Always include all required frontmatter fields
  4. Link to upstream entries where applicable
  5. Use the next available ID number

Pipeline Flow

Sources → Ideation → Ideas → Hypotheses → Experiments → Results
   ↑                                                        |
   └──────────────────────── Loop ──────────────────────────┘

Results feed back as sources. This is the core mechanic.

Code Style

  • TypeScript only, bun runtime
  • No Python, no npm/npx
  • Minimal dependencies
  • CLI-first philosophy
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. 2mo ago First seen · 49 lines · 424 tokens per session scan A 39639a7bce4c

Subscribe to this mod's changes

Ladder CLAUDE.md is an instructions file published in the GitHub repository danielmiessler/Ladder (268 stars, last pushed 7mo ago), licensed MIT. It adds 424 tokens to every session, about $0.0017 per session on Opus 5.5. 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 2026-08-30.

Related

Ladder CLAUDE.md compared with instructions from other repositories

Ladder CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Ladder CLAUDE.mddanielmiessler/LadderInstructions file2687mo agoMITA424Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode