What is shadow CLAUDE.md?

A set of instructions for an AI coding agent working in the Decision Shadow plugin repository.

Use it when modifying that repository, running its tests, or understanding how the plugin and its local copy fit together.

It explains the repository's layout, source-of-truth files, tests, and development constraints so changes are made in the right place.

How michal-bajer1/shadow configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to michal-bajer1/shadow. 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/michal-bajer1/shadow/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/michal-bajer1/shadow

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/michal-bajer1/shadow/claude-md/github.svg)](https://agentmods.dev/instructions/michal-bajer1/shadow/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/michal-bajer1/shadow/claude-md"><img src="https://agentmods.dev/badge/instructions/michal-bajer1/shadow/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/michal-bajer1/shadow/claude-md"><img src="https://agentmods.dev/badge/instructions/michal-bajer1/shadow/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 818 This file is loaded in full into every session.

When invoked 818 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.

Model	Per session	Once invoked
Fable 5.1	$0.00818	$0.00818
Opus 5.5	$0.00327	$0.00327
Sonnet 5.5	$0.00164	$0.00164
Haiku 4.5	$0.00082	$0.00082

Measured 2mo ago against content hash a11564e4ba5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

shadow 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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 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.

What this repo is

This is the source repository for the Decision Shadow Claude Code plugin. It both defines the plugin (under plugins/shadow/) and dogfoods it — the .claude/ directory installs and runs the plugin locally so that decisions made while developing it are captured using itself.

When modifying plugin files, always edit under plugins/shadow/. The .claude/plugins/shadow/ directory is the local installation copy; changes there are not the source of truth.

Running tests

bash tests/test_shadow.sh

The test suite creates isolated git repos in $TMPDIR and exercises all shadow-cli commands, the pre-commit hook, and session-orient.py. No Claude session required. There is no build step — shadow-cli is pure Python 3.8+ stdlib with no external dependencies.

Repository layout

plugins/shadow/          ← plugin source (the thing that gets published)
  bin/shadow-cli         ← the CLI (single Python file, ~830 lines)
  hooks/
    hooks.json           ← hook registry (SessionStart, PostCompact, PreToolUse)
    pre-commit-check.sh  ← blocks commits without .shadow/ staged
    session-orient.py    ← delivers decision brief at session start
  skills/                ← SKILL.md files for capture-decision, load-decisions, shadow-reference
  agents/                ← AGENT.md files for session-orient
docs/
  DECISION_SHADOW_SPEC.md   ← design rationale and full schema reference
  SHADOW_CLI_SPEC.md        ← CLI implementation details and output format
tests/
  test_shadow.sh
.shadow/                 ← decision records for this repo (dogfooding)

Architecture

The stable abstraction boundary

shadow-cli is the only component that reads and writes .shadow/ files. Skills, agents, and hooks all go through the CLI — they never manipulate decisions.jsonl directly. This means the file format can evolve without touching skill or agent prompts.

Read the full file on GitHub · 62 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.

2mo ago First seen · 62 lines · 818 tokens per session scan A a11564e4ba5a

Subscribe to this mod's changes

shadow CLAUDE.md is an instructions file published in the GitHub repository michal-bajer1/shadow (2 stars, last pushed 5mo ago), licensed MIT. It adds 818 tokens to every session, about $0.0033 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 2026-08-31.

shadow CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
shadow CLAUDE.mdmichal-bajer1/shadow	Instructions file	2	5mo ago	MIT	A	818	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

shadow: Instructions file for Claude Code