CLAUDE.md@packs/foundationA

CLAUDE.md@packs/foundation from revenantworks/claude-skills is a CLAUDE.md file: the standing instructions Claude Code reads in that repo.

Install it, pinned
mdr add revenantworks/claude-skills/packs/foundation/CLAUDE.md@git:20260917.fc8be8b

Pins git:20260917.fc8be8b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
CLAUDE.md file
Repository
revenantworks/claude-skills
Path
packs/foundation/CLAUDE.md
Versions recorded
10
Latest version
git:20260917.fc8be8b, committed Sep 17, 2026
First version recorded
Aug 17, 2026
Size
10,264 bytes
Repository stars
2
License
MIT

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

# Foundation Pack — router & conventions

The always-on companion to the **foundation** pack's eleven wrights. Each skill routes on its own description when invoked. This file is the standing context that makes them work *together*, so the right wright gets reached for without being named, and the pack's conventions hold across a session.

**Using it:** APPEND into your project root's `CLAUDE.md` (or into `~/.claude/CLAUDE.md` to cover every project) so Claude Code loads it automatically — both packs' routers can coexist in one file, and a copy would overwrite whichever router landed first. It also loads on its own when you work under `packs/foundation/` in the claude-skills repo. It is not a skill: nothing here is invoked; it is context.

## Reaching for the right wright

| The task | Wright | Say |
|---|---|---|
| Build, audit, port, or pack a skill, or a register pass on a skill's or pack's own files | **skillwright** | "build / audit a skill", "humanize / tighten this README", `skillwright` |
| Write, fix, or score a prompt | **promptwright** | "write / improve a prompt", `promptwright` |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add revenantworks/claude-skills/packs/foundation/CLAUDE.md@sha256:7a405d370d67c133

The line at the top of this page pins the label git:20260917.fc8be8b, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_nxp7pugvp4oxpbgw.svg)](https://markdownregistry.com/a/art_nxp7pugvp4oxpbgw)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 10 versions of this file, between Aug 17, 2026 and Sep 17, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
git:20260917.fc8be8b latest2026-09-17 fc8be8b 10,264 BA view · diff
git:20260915.4d41c9f2026-09-15 4d41c9f 10,197 BA view · diff
git:20260911.e8dc11a2026-09-11 e8dc11a 10,006 BA view · diff
git:20260911.4d94fe32026-09-11 4d94fe3 10,019 BA view · diff
git:20260909.4cfe7442026-09-09 4cfe744 9,218 BA view · diff
git:20260821.11306562026-08-21 1130656 9,113 BA view · diff
git:20260818.da246742026-08-18 da24674 9,264 BA view · diff
git:20260818.01a72fa2026-08-18 01a72fa 9,261 BA view · diff
git:20260818.11839302026-08-18 1183930 8,679 BA view · diff
git:20260817.848690a2026-08-17 848690a 8,037 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (10264 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

revenantworks/claude-skills · 2 stars · license MIT · pushed 2026-10-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_nxp7pugvp4oxpbgw
GET https://markdownregistry.com/api/v1/resolve?ref=revenantworks/claude-skills/packs/foundation/CLAUDE.md
GET https://markdownregistry.com/api/v1/blob/7a405d370d67c133e3fb61cc67fed4b40156748f0568525848a18d7e9581ee86

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: what a CLAUDE.md file is · keeping AGENTS.md and CLAUDE.md in sync · which agent file does what.

More from revenantworks/claude-skills

CLAUDE.md CLAUDE.md file
revenantworks/claude-skills · CLAUDE.md
git:20260922.1c3d3c5 · audit A · 2 stars
revenantworks-foundation-agentwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-agentwright/SKILL.md · Designs and audits the system around an autonomous or scheduled agent — everything but the prompt text — and emits it…
v1.2.10 · audit B · 2 stars
revenantworks-foundation-brandwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-brandwright/SKILL.md · Defines a brand and its voice — identity, naming, palette, taglines, firewall — and applies them on request across…
v1.6.1 · audit A · 2 stars
revenantworks-foundation-commwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-commwright/SKILL.md · Shapes any message to its channel and audience. Drafts human by default in a neutral professional voice; a specific…
v1.1.2 · audit A · 2 stars
revenantworks-foundation-dispatchwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-dispatchwright/SKILL.md · Runs a session's fan-out — turns one large request into tiered, budgeted, recoverable units and dispatches them…
v1.3.2 · audit A · 2 stars
revenantworks-foundation-evalwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-evalwright/SKILL.md · Authors and audits eval suites for skills, prompts, and agent specs — a build-time generator whose suites live in the…
v1.1.4 · audit A · 2 stars
revenantworks-foundation-lorewright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-lorewright/SKILL.md · Turns research into verified knowledge products, two modes. Trigger when someone wants a researched recommendation…
v1.1.10 · audit B · 2 stars
revenantworks-foundation-promptwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-promptwright/SKILL.md · Builds, scores, hardens, and red-teams LLM prompts — from a rough idea to a copy-paste-ready artifact — and picks which…
v1.5.14 · audit B · 2 stars
revenantworks-foundation-resumewright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-resumewright/SKILL.md · Owns every handoff — a committed session state (what already happened, verified against git) or a forward task brief…
v1.1.2 · audit A · 2 stars
revenantworks-foundation-rigwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-rigwright/SKILL.md · Builds the standing config Claude reads before work — a Claude Project's instructions and knowledge-file plan, a…
v1.1.10 · audit B · 2 stars
revenantworks-foundation-skillwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-skillwright/SKILL.md · Builds, audits, ports, and integrates install-ready Agent Skills passing best practices. Trigger to build, audit…
v1.5.0 · audit B · 2 stars
revenantworks-foundation-tokenwright SKILL.md skill
revenantworks/claude-skills · packs/foundation/skills/revenantworks-foundation-tokenwright/SKILL.md · Measures and shrinks the token footprint of LLM-facing artifacts — prompts, SKILL.md bodies, agent specs, CLAUDE.md…
v1.2.7 · audit B · 2 stars

Every file in revenantworks/claude-skills

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