rule-rewriter SKILL.md skillA
rule-rewriter from naveedharri/benai-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add naveedharri/benai-skills/rule-rewriter@git:20260916.a3b1e15Pins git:20260916.a3b1e15 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- naveedharri/benai-skills
- Path
plugins/all-skills/skills/rule-rewriter/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260916.a3b1e15, committed Sep 16, 2026
- First version recorded
- Aug 26, 2026
- Size
- 5,008 bytes
- Repository stars
- 78
- License
- MIT
Audit a CLAUDE.md or skill file for rules written for older Claude models and rewrite them for the Claude 5 generation. Finds one-sided rules, bare prohibitions, retired instructions, and aggressive language, then rewrites each into judgment plus the reason, or flags it for deletion. Use when the user says "rewrite my rules", "audit my CLAUDE.md", "fix my claude md", "rule rewriter", "my skills feel too strict", or after upgrading to a Claude 5 model.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Rule Rewriter Claude 5 models follow judgment better than they follow rules. A bare "never do X" gets ignored or overfitted; "X breaks because [reason], so avoid it" generalizes. This skill audits an instruction file and rewrites it accordingly. Grounded in Anthropic's published guidance: - Rules to judgment: https://claude.com/blog/the-new-rules-of-context-engineering-for-claude-5-generation-models - Give the why: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices - Remove verification instructions: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5 ## Process 1. **Locate the target.** Default to the CLAUDE.md in the current working folder. If the user names a skill or another file, use that. If nothing is found, ask for the path and stop. 2. **Inventory every instruction line.** Classify each into exactly one bucket: - **RETIRED**: instructions the model now does by itself. Delete candidates. Examples: "double-check your work", "verify before responding", "think step by step", "be thorough", "always re-read the file", "you are an expert...". …
Read the whole file at its exact version.
How to install
mdr add naveedharri/benai-skills/rule-rewriter@sha256:1561d2e9dcb0675bThe line at the top of this page pins the label git:20260916.a3b1e15, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_jamojogefl23bdv6)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Aug 26, 2026 and Sep 16, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260916.a3b1e15 latest | 2026-09-16 | a3b1e15 | 5,008 B | A | view · diff |
| git:20260903.821add1 | 2026-09-03 | 821add1 | 4,977 B | A | view · diff |
| git:20260826.76c256c | 2026-08-26 | 76c256c | 4,630 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5008 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
naveedharri/benai-skills · 78 stars · license MIT · pushed 2026-10-09 · branch develop
API
GET https://markdownregistry.com/api/v1/artifacts/art_jamojogefl23bdv6 GET https://markdownregistry.com/api/v1/resolve?ref=naveedharri/benai-skills/rule-rewriter GET https://markdownregistry.com/api/v1/blob/1561d2e9dcb0675b0a78328480806bf74cbc8cbe264e389a4b1b81d2207213fb
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.