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 skills add anilcancakir/claude-code --skill claude-md-rules-creatorgit clone --depth 1 https://github.com/anilcancakir/claude-codeWrote 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/claude-md-rules-creator)<a href="https://agentmods.dev/skills/anilcancakir/claude-code/claude-md-rules-creator"><img src="https://agentmods.dev/badge/skills/anilcancakir/claude-code/claude-md-rules-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 5.1 | $0.00060 | $0.09584 |
| Opus 5 | $0.00030 | $0.04792 |
| Sonnet 5 | $0.00012 | $0.01917 |
| Haiku 4.5 | $0.00006 | $0.00958 |
Grade A, and why
claude-md-rules-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 3d 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 — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md and Rules Creator
You are about to write or edit a CLAUDE.md, CLAUDE.local.md, or .claude/rules/*.md file. At runtime these three shapes are the SAME content type: Claude Code's memory loader discovers them, concatenates them with a fixed MEMORY_INSTRUCTION_PROMPT prefix, and the API layer prepends the result as a single <system-reminder> user message before the conversation starts. The model treats them all the same; the file shape just controls when each loads and how a human maintains it.
This skill is the playbook for picking the right shape, choosing the right scope, writing content that actually changes behavior, splitting bloated files, using @path imports, and debugging "Claude is not following my CLAUDE.md". Target is Opus 5. Same rules work for Sonnet 5 at lower cost and for Haiku 4.5, which supports no effort parameter.
Three jobs, not one
Writing a CLAUDE.md or rule splits into three tasks. Conflating them is the most common authoring mistake.
- Surrounding skill shape. None. CLAUDE.md and
.claude/rules/*.mdare not skills, not commands, not agents. They are plain markdown files the memory loader picks up. No frontmatter fields apply exceptpaths:(only on.claude/rules/*.md). Route throughac:skill-creatorONLY if you are wrapping CLAUDE.md authoring inside a custom slash command or skill. - CLAUDE.md / rule shape. Where the file lives (managed / user-global / project-team / project-personal), what file name (
CLAUDE.md/CLAUDE.local.md/.claude/rules/<topic>.md),paths:frontmatter for rules,@pathimports, HTML comments. This file teaches that. - Body content. The markdown text the model reads. This is a standing instruction set, a prompt at runtime. Route through
ac:prompt-writerfor prompt architecture, snippets, and Opus 5 tuning.
A great body in the wrong file shape (oversized, wrong scope, missing paths:, leaks personal preferences into a team file) never produces consistent behavior. A modest body in the right shape, sized below the adherence cliff, changes behavior every session.
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/CLAUDE.local.template.md 1.5 KB
- assets/CLAUDE.template.md 3.7 KB
- assets/global-CLAUDE.template.md 2.3 KB
- assets/rule.template.md 2.3 KB
- references/anti-patterns.md 18 KB
- references/content-rules.md 19 KB
- references/examples.md 12 KB
- references/hook-wiring.md 11 KB
- references/imports-and-paths.md 13 KB
- references/layered-context.md 20 KB
- references/loader-and-injection.md 17 KB
- references/lsp-wiring.md 6.8 KB
- references/rules-writing.md 18 KB
- references/scopes.md 13 KB
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.
- 3d ago Changed · +6 lines · -102 tokens per session ae7bb5f9b221
- 8d ago First seen · 391 lines · 162 tokens per session scan A 91d5425343ae
claude-md-rules-creator is a skill published in the GitHub repository anilcancakir/claude-code (3 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 9,584 once invoked, about $0.0003 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
dream
Prunes and consolidates the project's auto-memory to keep it minimal — deletes stale, wrong, or redundant memories, merges overlapping ones into existing files, and trims the index. Strong bias against growth: never creates new memory files and never stores new facts. Verifies staleness against the current codebase…
masterplan-detect
Suggest /masterplan import only when legacy masterplan bundle state files (docs/masterplan/ /state.yml at schema 5.x) exist without a matching v8 run. Generic planning artifacts (PLAN.md, TODO.md, ROADMAP.md, design docs, PR task lists) are NOT importable — no /masterplan import can ingest them; mention them only as…
guide
Open the showreel visual setup guide, or walk the user through installing the plugin's dependencies. Use when the user asks how to set up showreel, install its dependencies, pre-warm the capture motor, install vhs, or says "showreel guide", "setup guide", "como instalar o showreel".
showreel
Use when the user wants to explain or document something visually — annotated screenshots, feature demos, flow GIFs, terminal recordings, before/after comparisons — or says "take a screenshot", "record this flow", "make a gif of", "show how this works", "annotate this page", "demo this feature", "grava um gif", "tira…
code-craft
Professional code craftsmanship standards, especially how to write comments the right way. Use whenever writing or editing code, when adding comments or docstrings, during code review, or when the user asks for clean, production-quality, well-documented code. Covers comment discipline (explain why not what)…
audit-evidence
What an auditor is allowed to assert, and what it must cite. Preloaded into every praxis review auditor through the skills frontmatter field, so the rule exists once. Use whenever you are reviewing, auditing, or verifying a change and about to state a verdict: it defines the difference between a finding and a guess…