agent-rules-sync: Instructions file for Claude Code

CLAUDE.md

agent-rules-sync CLAUDE.md is an instructions file for Claude Code, Codex from dhruv-anand-aintech/agent-rules-sync. It costs 3,509 tokens per session, scanned C, original, MIT.

Release instructions for Agent Rules Sync, a Python tool that keeps rules aligned across AI coding assistants. They describe its tests, package files, version updates, and publishing workflow.

In plain words
What is it for?
Preparing changes, running the test suite, bumping the package version, updating the changelog, building distributions, and releasing them to PyPI, Python's package index.
Why use it?
They reduce release mistakes by specifying which files to update, which tests to run, and how to build and publish a new package version.

Instructions file for Claude CodeCodex

Written for Codex and Claude Code: runs codex exec, but also the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Codex.

This is dhruv-anand-aintech/agent-rules-sync's own configuration. It tells Claude Code and Codex how to work on agent-rules-sync 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 agent-rules-sync configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dhruv-anand-aintech/agent-rules-sync. 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/dhruv-anand-aintech/agent-rules-sync/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dhruv-anand-aintech/agent-rules-sync

Made for: Claude Code, Codex.

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 agent-rules-sync CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dhruv-anand-aintech/agent-rules-sync/claude-md.svg)](https://agentmods.dev/instructions/dhruv-anand-aintech/agent-rules-sync/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dhruv-anand-aintech/agent-rules-sync/claude-md"><img src="https://agentmods.dev/badge/instructions/dhruv-anand-aintech/agent-rules-sync/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,509 This file is loaded in full into every session.
When invoked 3,509 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.03509 $0.03509
Opus 5 $0.01754 $0.01754
Sonnet 5 $0.00702 $0.00702
Haiku 4.5 $0.00351 $0.00351

Measured 6d ago against content hash f9edd972e82e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

agent-rules-sync CLAUDE.md scanned grade C with 1 finding 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 6d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf dist/ build/ *.egg-info
CLAUDE.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Rules Sync - Project Context

Quick Facts

  • Project: Agent Rules Sync - Synchronize rules across AI coding assistants
  • Language: Python 3.8+
  • Main File: agent_rules_sync.py (single-file module with daemon support)
  • Tests: Located in tests/ directory (29 tests, all passing)
  • Package: Published on PyPI - https://pypi.org/project/agent-rules-sync/

Release Workflow

1. Prepare Changes

  • Make code changes and commit to git
  • Run tests: /usr/bin/python3 -m pytest tests/ -v
  • Ensure all tests pass before releasing

2. Version Bump

Update THREE files to bump version (e.g., from 1.2.2 to 1.2.3):

File 1: pyproject.toml (line 7)

version = "1.2.3"

File 2: CHANGELOG.md (add entry at top)

## [1.2.3] - 2026-02-07

### 🧪 Category Name
- Feature description 1
- Feature description 2

File 3: setup.py - NO CHANGE NEEDED

  • It reads version from pyproject.toml automatically

Commit the version bump:

git add pyproject.toml CHANGELOG.md
git commit -m "chore: bump version to 1.2.3 with [description]"
git push origin main

3. Build Package

# Clean old builds
rm -rf dist/ build/ *.egg-info

# Build wheel and sdist using miniforge python
python3.10 -m build

Output: dist/agent_rules_sync-1.2.3.tar.gz and dist/agent_rules_sync-1.2.3-py3-none-any.whl

4. Publish to PyPI

# Upgrade twine if needed
python3.10 -m pip install --upgrade twine

# Upload to PyPI (uses ~/.pypirc credentials)
python3.10 -m twine upload dist/agent_rules_sync-1.2.3* --skip-existing

Verify at: https://pypi.org/project/agent-rules-sync/

5. Create GitHub Release

# Create and push git tag
git tag -a v1.2.3 -m "test: add daemon watch detection tests"
git push origin v1.2.3

# Create GitHub release (with auto-generated notes)
gh release create v1.2.3 --title "v1.2.3: Test Coverage Improvements" --notes "Release notes here"

Verify at: https://github.com/dhruv-anand-aintech/agent-rules-sync/releases

Read the full file on GitHub · 297 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. 6d ago First seen · 297 lines · 3,509 tokens per session scan C f9edd972e82e

Subscribe to this mod's changes

agent-rules-sync CLAUDE.md is an instructions file published in the GitHub repository dhruv-anand-aintech/agent-rules-sync (7 stars, last pushed 1mo ago), licensed MIT. It adds 3,509 tokens to every session, about $0.0175 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.