Kibertum/tausik-core
AI coding agents can't quietly fake "done". Signed ed25519 receipts prove the gates actually ran — bound to the commit, verifiable offline. Fail-closed hooks block the edit, not the PR. Harness engineering over Claude Code, Cursor, Codex, Q
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/Kibertum/tausik-core 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 Kibertum/tausik-core/harness/skills/_profile-demo .claude/skills/_profile-demo $ npx degit Kibertum/tausik-core/harness/skills/checkpoint .claude/skills/checkpoint $ npx degit Kibertum/tausik-core/harness/skills/commit .claude/skills/commit $ npx degit Kibertum/tausik-core/harness/skills/debug .claude/skills/debug $ npx degit Kibertum/tausik-core/harness/skills/end .claude/skills/end $ npx degit Kibertum/tausik-core/harness/skills/explore .claude/skills/explore $ npx degit Kibertum/tausik-core/harness/skills/interview .claude/skills/interview $ npx degit Kibertum/tausik-core/harness/skills/plan .claude/skills/plan $ npx degit Kibertum/tausik-core/harness/skills/reason .claude/skills/reason $ npx degit Kibertum/tausik-core/harness/skills/review .claude/skills/review $ npx degit Kibertum/tausik-core/harness/skills/run .claude/skills/run $ npx degit Kibertum/tausik-core/harness/skills/ship .claude/skills/ship $ npx degit Kibertum/tausik-core/harness/skills/start .claude/skills/start $ npx degit Kibertum/tausik-core/harness/skills/task .claude/skills/task $ npx degit Kibertum/tausik-core/harness/skills/tausik-memory .claude/skills/tausik-memory
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 (15)
Similar rigs
nicodiansk/turbocharge
Opinionated engineering pipeline for Claude Code: 10 skills, 6 agents, 2 hooks, 1 workflow. Replaces ad-hoc agent sprawl with brainstorm → story → plan → build → review → ship.
Pragmatist 5.4k tok · · Q5
itw-creative-works/workkit
The issue-pipeline workflow system as a Claude Code plugin: GitHub Issues as the work-item SSOT, labels as the pipeline, guard hooks, a manager crew, and the skills from build to ship.
Pragmatist 3.9k tok · · Q0
nicodiansk/turboflow
Opinionated engineering pipeline for Claude Code with 10 skills, 5 agents, 2 hooks. Replaces ad-hoc agent sprawl with brainstorm → story → plan → build → review → ship.
Pragmatist 2.1k tok · · Q0
schen22/claude-config
My Claude Code setup: rules, skills, hooks and the research-round plugin I use to build products with AI
Skill Collector 1.1k tok · · Q15