shadowsky CLAUDE.md

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/dmoskov/shadowsky/claude-md

Clone the repo

git clone --depth 1 https://github.com/dmoskov/shadowsky

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/dmoskov/shadowsky/claude-md.svg)](https://agentmods.dev/instructions/dmoskov/shadowsky/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dmoskov/shadowsky/claude-md"><img src="https://agentmods.dev/badge/instructions/dmoskov/shadowsky/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,176 This file is loaded in full into every session.

When invoked 1,176 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.

Model	Per session	Once invoked
Fable 5	$0.01176	$0.01176
Opus 5	$0.00588	$0.00588
Sonnet 5	$0.00235	$0.00235
Haiku 4.5	$0.00118	$0.00118

Measured 2d ago against content hash b5f42c265ee8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shadowsky 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Universal Instructions

See: /Users/moskov/Code/CLAUDE.md for universal coding standards

Project: BSKY

Overview

This is the CLAUDE.md file for your project. Add project-specific instructions here.

Git Workflow

Branch Strategy

main — Development/staging branch. All feature work and fixes land here first. Auto-deploys to main.asphodel.is.
prod — Production branch. Deploys the web app (including public/ static files like OAuth client metadata). Auto-deploys to asphodel.is.
task/* — Feature/task branches created from main.

To deploy to production: merge main into prod and push. The prod branch auto-deploys to asphodel.is (production); main auto-deploys to main.asphodel.is (staging).

Rules

NO automatic commits or pushes: Never run git commit or git push automatically. Always wait for explicit user approval before committing or pushing changes.
Show the user what changes would be committed and let them decide when to commit and push.
ALWAYS run formatting checks before pushing: Before pushing to any branch, run npm run test:format to check for formatting issues. If there are issues, run npm run fix:format to fix them automatically.

Using the Push Script

A push script is available at scripts/push.sh that automatically runs pre-push checks:

# Basic usage (pushes to current branch)
./scripts/push.sh

# Push to specific branch
./scripts/push.sh origin feature-branch

# Force push (use with caution)
./scripts/push.sh --force

# Push with any git push arguments
./scripts/push.sh --set-upstream origin my-branch

The push script will:

Check for uncommitted changes
Run npm run test:format to check code formatting
Run npm run build to ensure the project builds successfully
Only push if all checks pass

If formatting issues are found, the script will suggest running npm run fix:format to fix them automatically.

UI Design Preferences

No headers in feed views: Don't add title/description headers at the top of feed components. The user prefers a clean, header-free interface.
Feed views should start directly with the content or feed selection controls.

Read the full file on GitHub · 105 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.

2d ago First seen · 105 lines · 1,176 tokens per session scan A b5f42c265ee8

Subscribe to this mod's changes

shadowsky CLAUDE.md is an instructions file published in the GitHub repository dmoskov/shadowsky (17 stars, last pushed 3d ago), licensed MIT. It adds 1,176 tokens to every session, about $0.0059 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 2026-09-01.

Git and workflow

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