decision-linter CLAUDE.md

decision-linter CLAUDE.md is an instructions file for Claude Code from dixalex/decision-linter. It costs 258 tokens per session, scanned A, original, MIT.

A Claude Code skill that checks the reasoning behind important decisions before you commit to them. It considers whether the situation rewards intuition or needs a more structured process.

In plain words
What is it for?
Use it to review a proposal, sanity-check assumptions, compare alternatives, or produce a short decision memo for a pull request, chat, proposal, or decision log.
Why use it?
It helps expose assumptions, blind spots, and the risk of making a hard-to-reverse choice too quickly.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions 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 instructions/dixalex/decision-linter/claude-md
Clone the repo
git clone --depth 1 https://github.com/dixalex/decision-linter

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 decision-linter CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dixalex/decision-linter/claude-md.svg)](https://agentmods.dev/instructions/dixalex/decision-linter/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dixalex/decision-linter/claude-md"><img src="https://agentmods.dev/badge/instructions/dixalex/decision-linter/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 258 This file is loaded in full into every session.
When invoked 258 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 5.1 $0.00258 $0.00258
Opus 5 $0.00129 $0.00129
Sonnet 5 $0.00052 $0.00052
Haiku 4.5 $0.00026 $0.00026

Measured 5d ago against content hash 0cf3ee7906da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

decision-linter 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 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.

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 · 30 lines

What it actually says

Decision Linter — AI Skill for Pre-Commitment Judgment Checks

What This Is

A Claude Code skill that runs a structured judgment check before consequential decisions. Scores the decision environment as Kind (trust gut) or Wicked (impose structure), runs consider-the-opposite debiasing, surfaces blind spots, and outputs a paste-ready judgment memo.

Based on: Kahneman-Klein (conditions for intuitive expertise), Hogarth (kind vs wicked environments), Tetlock (superforecasting), Morewedge (debiasing interventions).

Installation

/plugin marketplace add dixalex/decision-linter

Or place skills/decision-linter/ in your .claude/skills/ folder.

Dependencies

None. This skill uses only Claude's reasoning — no external tools, MCP servers, or plugins required.

Usage

Invoke with /decision-linter or naturally: "check my assumptions", "lint this decision", "sanity check this proposal".

The skill also auto-triggers when it detects you're about to commit to a high-stakes, low-reversibility direction.

Output

Produces a paste-ready judgment memo (under 300 words) suitable for PRs, Slack, proposals, or decision logs.

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 · 30 lines · 258 tokens per session scan A 0cf3ee7906da

Subscribe to this mod's changes

decision-linter CLAUDE.md is an instructions file published in the GitHub repository dixalex/decision-linter (2 stars, last pushed 4mo ago), licensed MIT. It adds 258 tokens to every session, about $0.0013 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

skills-for-humanity CLAUDE.md

Claude Code instructions for human-avatar/skills-for-humanity, covering skills-for-humanity, structure, naming convention, skill.md format and category command format.

human-avatar/skills-for-humanity · 698 tokens

anvil CLAUDE.md

Claude Code instructions for mulkatz/anvil, covering anvil — adversarial thinking plugin, what this is, architecture, key files and documentation.

mulkatz/anvil · 1,139 tokens

agent-skills CLAUDE.md

Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.

mindbox-cloud/agent-skills · 1,143 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens