kendrick/working-memory-kit
Persistent project context for AI coding agents. One always-read file, six on demand. Installs in one command on macOS and Windows.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit kendrick/working-memory-kit/.claude ./rig-working-memory-kit # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit kendrick/working-memory-kit/.claude/skills/hydrate-discover .claude/skills/hydrate-discover $ npx degit kendrick/working-memory-kit/.claude/skills/hydrate-draft .claude/skills/hydrate-draft $ npx degit kendrick/working-memory-kit/.claude/skills/hydrate-extract .claude/skills/hydrate-extract $ npx degit kendrick/working-memory-kit/.claude/skills/hydrate-propose .claude/skills/hydrate-propose $ npx degit kendrick/working-memory-kit/.claude/skills/hydrate-reconcile .claude/skills/hydrate-reconcile $ npx degit kendrick/working-memory-kit/template/.claude/skills/update-working-memory .claude/skills/update-working-memory
$ curl -fsSL --create-dirs -o .claude/agents/hydrator.md https://raw.githubusercontent.com/kendrick/working-memory-kit/main/.claude/agents/hydrator.md $ curl -fsSL --create-dirs -o .claude/agents/working-memory-synchronizer.md https://raw.githubusercontent.com/kendrick/working-memory-kit/main/template/.claude/agents/working-memory-synchronizer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (6)
Subagents (2)
| hydrator | > |
| working-memory-synchronizer | > |
Permissions
deny (0)
—
ask (0)
—
allow (5)
Read(/~/.claude/plugins/cache/superpowers-marketplace/superpowers/4.0.0/skills/subagent-driven-development/**)
Bash(git -C * status)
Edit(/.claude/skills/hydrate-reconcile/**)
Read(//tmp/working-memory-kit-emerson/**)
Read(//private/tmp/working-memory-kit-emerson/**)
Similar rigs
anomalyco/opencode
The open source coding agent.
Pragmatist 4.2k tok ·
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Pragmatist 1.6k tok ·
Shubhamsaboo/awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
Pragmatist 4.2k tok ·
garrytan/gstack
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Pragmatist 8.8k tok ·