Home / jellydn / my-ai-tools · configs/claude/CLAUDE.md · GitHub

CLAUDE.md@configs/claude claudeA

CLAUDE.md@configs/claude is agent-read markdown (claude) from jellydn/my-ai-tools.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Claude Code Guidelines

Use judgment. These instructions define outcomes, not a mandatory workflow.

## Token-Efficient Sessions

- Keep responses concise and actionable. Lead with conclusions, file paths, and verification results.
- Scope discovery to the task. Prefer targeted graph, `fff`, `rg`, or `fd` queries over broad searches and full-file dumps.
- Limit command output with filters, path scopes, and line ranges. Do not load documentation until it is relevant.
- Run `/context` during long sessions. Use `/clear` after finishing a task or when switching to unrelated work.
- Use `/handoffs` and `/pickup` when useful context must survive a reset.

## Working with Advanced Models (Fable/4.8+)

- You are more capable than the examples given here. These guidelines provide context and outcomes, not prescriptive steps. Use judgment and discovery.
- For a comprehensive guide on capability overhang, finding unknowns, and being unreasonable (in the best way), read `~/.ai-tools/fable-guide.md`. Do not load it for routine work.

## Discovery and Planning

For familiar, focused work, proceed with existing patterns. For unfamiliar or complex work:
…

Read the whole file at its exact version.

How to install

Latest version
mdr add jellydn/my-ai-tools/configs/claude/CLAUDE.md@git:20260730.6dd81c4
Exact content
mdr add jellydn/my-ai-tools/configs/claude/CLAUDE.md@sha256:435cf47606715c38

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_breefqgivoqwlj3q.svg)](https://markdownregistry.com/a/art_breefqgivoqwlj3q)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260730.6dd81c4 latest2026-07-30 6dd81c4 4,771 BA view · diff
git:20260709.ad6f0592026-07-09 ad6f059 3,757 BA view · diff
git:20260708.5f081922026-07-08 5f08192 3,759 BA view · diff
git:20260614.056e8472026-06-14 056e847 2,116 BA view · diff
git:20260614.dff68732026-06-14 dff6873 2,010 BA view

Audit of the latest version

A  14 of 14 checks passed. Deterministic, no model, same answer every run.
  • pass: Size between 200 bytes and 200 KB (4771 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

GitHub

jellydn/my-ai-tools · 121 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_breefqgivoqwlj3q
GET https://markdownregistry.com/api/v1/resolve?ref=jellydn/my-ai-tools/configs/claude/CLAUDE.md
GET https://markdownregistry.com/api/v1/blob/435cf47606715c38178124381bd23090d09733866ad03bb1facf28b689b6e2e3

Your agent 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.

More from jellydn/my-ai-tools

AGENTS.md agents
jellydn/my-ai-tools · AGENTS.md
git:20260805.03f0789 · audit A · 121 stars
AGENTS.md@configs/amp agents
jellydn/my-ai-tools · configs/amp/AGENTS.md
git:20260913.e2e25be · audit A · 121 stars
accountable-engineering skill
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/accountable-engineering/SKILL.md · Use explicit human checkpoints for architecture, security, rollout, or operational decisions.
git:20260913.e2e25be · audit A · 121 stars
adr skill
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/adr/SKILL.md · Record architecture decisions with ADRs — captures why, alternatives considered, and consequences
git:20260814.d1987f5 · audit A · 121 stars
blindspot-pass skill
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/blindspot-pass/SKILL.md · Inspect history and architecture for hidden constraints before risky cross-cutting changes.
git:20260913.e2e25be · audit A · 121 stars
capability-experiments skill
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/capability-experiments/SKILL.md · Build an interactive report or experiment when the user asks to explore model capabilities.
git:20260913.e2e25be · audit B · 121 stars
code-quality-review skill
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/code-quality-review/SKILL.md · Audit a diff for structural maintainability and unnecessary complexity.
git:20260913.e2e25be · audit A · 121 stars
code-review skill
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/code-review/SKILL.md · Review a branch, PR, or worktree diff for repository conventions and stated intent.
git:20260913.e2e25be · audit A · 121 stars
codemap skill
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/codemap/SKILL.md · Create a seven-document architecture map when the user asks to map a codebase.
git:20260913.e2e25be · audit A · 121 stars
commit-atomic skill
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/commit-atomic/SKILL.md · Group staged changes into atomic commits with commitizen convention
git:20260814.d1987f5 · audit A · 121 stars
context-discovery skill
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/context-discovery/SKILL.md · Use MCP tools to trace behavior that spans multiple modules or history sources.
git:20260913.e2e25be · audit A · 121 stars
doc-search skill
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/doc-search/SKILL.md · Search project documentation — ADRs, wiki entries, conventions via ripgrep, qmd, fff, and ctx
git:20260814.d1987f5 · audit A · 121 stars

Every file in jellydn/my-ai-tools

Browse by kind, by grade A, or by owner.