agentrigs
+ submit rig
~ / rigs / Fergana-Labs / stash

Fergana-Labs/stash

Open-source infrastructure for agents that learn from experience. Capture production traces and turn lessons into reusable knowledge and skills.

↗ GitHub ★ 333 mit updated 3d ago project Claude CodeCodexGemini CLI Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~1.3k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/Fergana-Labs/stash

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 Fergana-Labs/stash/docs/skills/brief .claude/skills/brief
$ npx degit Fergana-Labs/stash/docs/skills/cleanup .claude/skills/cleanup
$ npx degit Fergana-Labs/stash/docs/skills/overview .claude/skills/overview
$ npx degit Fergana-Labs/stash/docs/skills/resurface .claude/skills/resurface
$ npx degit Fergana-Labs/stash/docs/skills/slides .claude/skills/slides

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 (5)

briefcleanupoverviewresurfaceslides

Similar rigs

cmgmyr/hive
Run a crew of Claude Code and Codex workers from one lead session: visible tmux panes, exact state from hooks, one local SQLite store.
★ 2 project Claude CodeCodex 4 skills 2 hooks today
Pragmatist 6.0k tok ·
mkay1375/claude-config
User-level Claude Code config (~/.claude)
★ 1 setup Claude Code 4 skills 4 hooks 5d ago
Automator 828 tok ·
latent-variable/userscope
One user-scope brain every agent CLI reads: Claude Code, Codex, Antigravity/Gemini, Pi. Clone to ~/.agents, let your agent onboard you.
★ 1 setup Codex 5 skills 2mo ago
Pragmatist 3.2k tok ·
anton-dergunov/agentic-paper-library
Reading and organising a research-paper library with a coding agent: papers converted to Markdown the agent can read and cite, and skills for adding, reading and reviewing them.
★ 0 collection Claude CodeCodex 6 skills today
Pragmatist 741 tok ·
copied ✓