setup SKILL.md skillB

setup from awrshift/agent-memory-kit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add awrshift/agent-memory-kit/setup@git:20261022.c74602a

Pins git:20261022.c74602a in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
awrshift/agent-memory-kit
Path
plugins/memory-kit/skills/setup/SKILL.md
Versions recorded
7
Latest version
git:20261022.c74602a, committed Oct 22, 2026
First version recorded
Sep 2, 2026
Size
14,691 bytes
Repository stars
34
License
MIT

Adopt the Memory Kit in THIS repository — scaffold the memory layers, decide how the kit coexists with Claude Code's native auto memory, and install safe permission rails (`/memory-kit:setup rails` re-runs only the rails step on an adopted repo). Use when the user says "/memory-kit:setup", "/memory-kit:setup rails", "set up the memory kit", "adopt the kit here", "настрой кит", or when a session starts in a repo where the kit plugin is installed but no .claude/memory/MEMORY.md exists.

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

# /memory-kit:setup — adopt the kit in an existing repository

The plugin ships behaviour; the repository owns the state. This skill creates that state —
**always asking before the first write**, and never touching files the repo already has.

Running without a user who can answer (a headless or `-p` run)? Then "offer" means **skip and
report**: take the documented default where one exists, install nothing that the skill marks as
opt-in, and finish with a list of what was deliberately not installed and what question is still
open. Never invent a preference on the user's behalf and never present a skipped step as done.

## Step 0 — look before you write

Report in two lines what already exists: `.claude/memory/MEMORY.md`, `context/handoffs/`,
`knowledge/`, `projects/`, an existing documentation home (`docs/`, `doc/`, `documentation/`),
`.claude/settings.json`, `.gitignore`, and whether this repo already holds work of its own —
code, or documents other than a bare README (a real project) — or is effectively empty (a fresh
memory workspace). Being a git repo decides nothing; content does. Everything after this is a proposal the user
confirms once, not a sequence of prompts.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add awrshift/agent-memory-kit/setup@sha256:fd95c4e571cb3be7

The line at the top of this page pins the label git:20261022.c74602a, 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_dvowr5rsgs6blnyl.svg)](https://markdownregistry.com/a/art_dvowr5rsgs6blnyl)

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

Versions

The registry has recorded 7 versions of this file, between Sep 2, 2026 and Oct 22, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
git:20261022.c74602a latest2026-10-22 c74602a 14,691 BB view · diff
git:20261022.df602ef2026-10-22 df602ef 15,772 BB view · diff
git:20261007.2be0b0a2026-10-07 2be0b0a 15,785 BB view · diff
git:20260928.62b86852026-09-28 62b8685 15,791 BB view · diff
git:20260926.f43b1242026-09-26 f43b124 15,790 BB view · diff
git:20260917.4c352d02026-09-17 4c352d0 12,573 BB view · diff
git:20260902.30f55392026-09-02 30f5539 12,287 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No instruction to read or print local credentials (matched: Read(./.env)", "Edit(./.env)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (14691 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 base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

awrshift/agent-memory-kit · 34 stars · license MIT · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_dvowr5rsgs6blnyl
GET https://markdownregistry.com/api/v1/resolve?ref=awrshift/agent-memory-kit/setup
GET https://markdownregistry.com/api/v1/blob/fd95c4e571cb3be75265e980a19f963f30f44d6fc5f04c3a13e21b61924add48

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.

More from awrshift/agent-memory-kit

CLAUDE.md CLAUDE.md file
awrshift/agent-memory-kit · CLAUDE.md
git:20261022.c74602a · audit A · 34 stars
close-session SKILL.md skill
awrshift/agent-memory-kit · plugins/memory-kit/skills/close-session/SKILL.md · End-of-session ritual — audit today's patterns against accumulated memory, propose promotions, refresh MEMORY.md, and…
git:20261022.df602ef · audit A · 34 stars
code-sync SKILL.md skill
awrshift/agent-memory-kit · plugins/memory-kit/skills/code-sync/SKILL.md · Reconcile the project's documents with what the code now shows, after a merge or at the end of a build: spec statuses…
git:20261022.df602ef · audit A · 34 stars
document SKILL.md skill
awrshift/agent-memory-kit · plugins/memory-kit/skills/document/SKILL.md · Write the human-facing prose about a change — PR body · changelog entry · release note · postmortem — and put it in the…
git:20261022.df602ef · audit A · 34 stars
memory-audit SKILL.md skill
awrshift/agent-memory-kit · plugins/memory-kit/skills/memory-audit/SKILL.md · Audit MEMORY.md against the memory discipline — oversized sections, settled multi-session patterns that belong in…
git:20261022.df602ef · audit A · 34 stars
qa-sweep SKILL.md skill
awrshift/agent-memory-kit · plugins/memory-kit/skills/qa-sweep/SKILL.md · Run a multi-lens agent QA sweep of the RUNNING product: spawn `qa` agents (one per lens — user-flow · edge-state ·…
git:20260924.2010481 · audit A · 34 stars
second-opinion SKILL.md skill
awrshift/agent-memory-kit · plugins/memory-kit/skills/second-opinion/SKILL.md · Cross-check the agent's own answer with independent reviewers before bringing it to the user. Use when the user says…
git:20261022.af5bf98 · audit A · 34 stars
session-review SKILL.md skill
awrshift/agent-memory-kit · plugins/memory-kit/skills/session-review/SKILL.md · End-of-session adversarial review loop. Assemble the session's work into a role-assigned, self-contained brief, then…
git:20260818.a8b21c0 · audit A · 34 stars
system-audit SKILL.md skill
awrshift/agent-memory-kit · plugins/memory-kit/skills/system-audit/SKILL.md · Periodic evidence-based self-audit of the whole agent system — the orchestrator, its docs/SSOTs, rules, memory…
git:20260926.f43b124 · audit A · 34 stars
tour SKILL.md skill
awrshift/agent-memory-kit · plugins/memory-kit/skills/tour/SKILL.md · Interactive walkthrough of the Memory Kit system using the user's actual project files. Use when the user says…
git:20261022.c74602a · audit A · 34 stars

Every file in awrshift/agent-memory-kit

Other files named setup

setup SKILL.md skill
garrytan/gbrain · plugin/skills/setup/SKILL.md · Add keyless GBrain memory to an existing agent, or connect a hosted brain while preserving identity and configuration
git:20261010.47d0faf · audit A · 31,074 stars
setup SKILL.md skill
nanocoai/nanoclaw · .claude/skills/setup/SKILL.md · Run initial NanoClaw setup. Use when user wants to install NanoClaw, configure it, or go through first-time setup…
git:20260606.14dba9b · audit A · 30,979 stars
setup SKILL.md skill
garrytan/gbrain · skills/setup/SKILL.md · Add keyless GBrain memory to an existing agent, or connect a hosted brain while preserving identity and configuration
git:20261007.590bb9a · audit A · 31,074 stars
setup SKILL.md skill
tencent/teamai-cli · skill-data/setup/SKILL.md · TeamAI day 0 and repo lifecycle: create a team repo as admin, join an existing team as a member, manage members, roles…
git:20261014.a1f4e73 · audit A · 5,609 stars
setup SKILL.md skill
alsk1992/cloddsbot · src/skills/bundled/setup/SKILL.md · Setup Wizard — Configure environment for all skills
git:20260208.767d1d8 · audit A · 2,990 stars
setup SKILL.md skill
feder-cr/invisible_playwright_mcp · skills/setup/SKILL.md · What the invisible_playwright_mcp browser server needs on this machine - the patched Firefox it drives, which the…
git:20260923.a602cff · audit B · 1,345 stars
setup Cursor rule
sipyourdrink-ltd/bernstein · .cursor/rules/setup.mdc · Setup
git:20260521.b455a7c · audit A · 1,310 stars
setup SKILL.md skill
fcakyon/claude-codex-settings · plugins/overleaf-skills/skills/setup/SKILL.md · This skill should be used when user asks to "set up overleaf", "configure overleaf cookie", "overleaf auth failed"…
git:20260502.ad8603b · audit A · 1,181 stars

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