nabondance/strata
See how your agent context evolved across Git history.
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
Copy this rig
# review before running: this installs third-party code
$ npx degit nabondance/strata/.claude ./rig-strata # 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 nabondance/strata/.agents/skills/pr-screenshots .claude/skills/pr-screenshots $ npx degit nabondance/strata/skills/strata-interpret .claude/skills/strata-interpret
$ curl -fsSL --create-dirs -o .claude/agents/strata-reviewer.md https://raw.githubusercontent.com/nabondance/strata/main/.claude/agents/strata-reviewer.md This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (2)
Subagents (1)
| strata-reviewer model: inherit | Read-only review of Strata history, provider classification, measurement, and report privacy changes. |
Similar rigs
nanosite-ai/nanoflow
Run Claude Code tasks in parallel without losing track: each in its own worktree and ports, followed from ticket to PR to CI to teardown. By nanosite.ai
Minimalist 267 tok · · Q0
NickolasBenakis/agent-playbook
A small playbook for coding agents (Claude Code plugin, Codex, bb): 9 rules, 6 workflow skills, a reviewer and guard hooks, tested head-to-head against the plain model.
Pragmatist 1.4k tok · · Q5
Venkateshvenki404224/shipcraft-skills
Four Claude Code agent skills: map large work, slice it into shippable phases, pick the right data structures, deepen the architecture.
Skill Collector 672 tok · · Q0
levy-street/world-of-claudecraft
—
Orchestrator 19.2k tok · · Q34