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.
npx agentmods add skills/anilcancakir/claude-code-plugin/rule-creatornpx skills add anilcancakir/claude-code-plugin --skill rule-creatorgit clone --depth 1 https://github.com/anilcancakir/claude-code-pluginWrote 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.
[](https://agentmods.dev/skills/anilcancakir/claude-code-plugin/rule-creator)<a href="https://agentmods.dev/skills/anilcancakir/claude-code-plugin/rule-creator"><img src="https://agentmods.dev/badge/skills/anilcancakir/claude-code-plugin/rule-creator.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00042 | $0.01495 |
| Opus 5 | $0.00021 | $0.00747 |
| Sonnet 5 | $0.00008 | $0.00299 |
| Haiku 4.5 | $0.00004 | $0.00150 |
Grade A, and why
rule-creator 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create path-scoped rules that auto-inject when Claude Code reads, writes, or edits matching files. Rules hold "how to code HERE" — CLAUDE.md holds "what this project IS".
Context Layer Stack
~/.claude/CLAUDE.md ← always (global)
./CLAUDE.md ← always (project)
.claude/rules/<name>.md ← ON-DEMAND when matching file touched
CLAUDE.md and rules are visible simultaneously. Any overlap = wasted tokens. Rules are ADDITIVE — never duplicating CLAUDE.md, never re-stating what my-coding already covers.
Two-Tier Rules
| Tier | Scope | Lines | Example |
|---|---|---|---|
| Stack | All files of a language | 10-20 | flutter.md → lib/**/*.dart |
| Domain | Specific module | 15-40 | database.md → lib/src/database/**/*.dart |
Stack and domain globs can overlap — both inject when a domain file is touched. This is intentional: stack provides general conventions, domain adds deep API knowledge.
Core Process
1. Identify Scope
Determine which files need this rule. Define the narrowest glob that covers the affected area:
- Language-wide:
lib/**/*.dart,src/**/*.ts - Module-specific:
src/api/**/*.ts,app/Http/Controllers/**/*.php - Test files:
test/**/*_test.dart,tests/**/*.test.ts
Avoid **/* — too broad. Rules must add value only when the matched files are being touched.
2. Classify Tier
- Stack rule (10-20 lines): applies to all files of a language/framework — import style, naming, general conventions
- Domain rule (15-40 lines): applies to a specific module — API patterns, must-know method signatures, domain-specific gotchas
3. Dedup Check
Read these sources before writing any rule content:
./CLAUDE.md— project-wide conventions already stated~/.claude/CLAUDE.md— global workflow rules~/.claude/skills/my-coding/SKILL.md— general coding standards
Apply this algorithm to each proposed convention:
- Exact match found in any source → skip it
- Semantic overlap (broader rule covers this case) → skip it
- Conflict (proposed rule contradicts an existing rule) → flag for user decision, present both, ask which takes precedence
- Complement (adds specificity to a broad rule) → keep it
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.
- 4d ago First seen · 146 lines · 42 tokens per session scan A dc2373c291d6
rule-creator is a skill published in the GitHub repository anilcancakir/claude-code-plugin (2 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 1,495 once invoked, about $0.0002 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.
Other skills, from other repositories
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
python-package-management
Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.