~ / rigs / nowespojrzenie / HEXAGRAM

nowespojrzenie/HEXAGRAM

Epistemic discipline for AI assistants — truth statuses, an error registry, mutation-tested guards. Plain files, git as memory. Core in Polish; the assistant speaks your language.

↗ GitHub ★ 1 MIT updated 8d ago project Claude CodeCodex
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~7.3k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details
Quality 15/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit nowespojrzenie/HEXAGRAM/szablony/gosc/.claude ./rig-hexagram  # 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 nowespojrzenie/HEXAGRAM/skills/ai-agent-drift-detection .claude/skills/ai-agent-drift-detection
$ npx degit nowespojrzenie/HEXAGRAM/skills/ai-agent-error-memory-registry .claude/skills/ai-agent-error-memory-registry
$ npx degit nowespojrzenie/HEXAGRAM/skills/ai-agent-verify-success-claims .claude/skills/ai-agent-verify-success-claims
$ npx degit nowespojrzenie/HEXAGRAM/skills/ai-hallucination-truth-status .claude/skills/ai-hallucination-truth-status
$ npx degit nowespojrzenie/HEXAGRAM/skills/ai-interview-longitudinal .claude/skills/ai-interview-longitudinal
$ npx degit nowespojrzenie/HEXAGRAM/skills/ai-journal-space .claude/skills/ai-journal-space
$ npx degit nowespojrzenie/HEXAGRAM/skills/ai-personas-not-modes .claude/skills/ai-personas-not-modes
$ npx degit nowespojrzenie/HEXAGRAM/skills/ai-preregistration-confirmation-bias .claude/skills/ai-preregistration-confirmation-bias
$ npx degit nowespojrzenie/HEXAGRAM/skills/ai-real-deadlines-vs-felt-urgency .claude/skills/ai-real-deadlines-vs-felt-urgency
$ npx degit nowespojrzenie/HEXAGRAM/skills/ai-self-audit-without-hedging .claude/skills/ai-self-audit-without-hedging
$ npx degit nowespojrzenie/HEXAGRAM/skills/ai-stop-before-not-narrate-after .claude/skills/ai-stop-before-not-narrate-after
$ npx degit nowespojrzenie/HEXAGRAM/skills/ai-three-gates-before-output .claude/skills/ai-three-gates-before-output
$ npx degit nowespojrzenie/HEXAGRAM/skills/astro-six-element-lens .claude/skills/astro-six-element-lens
$ npx degit nowespojrzenie/HEXAGRAM/skills/astro-transit-window-boundaries .claude/skills/astro-transit-window-boundaries
$ npx degit nowespojrzenie/HEXAGRAM/skills/voice-profile-from-own-texts .claude/skills/voice-profile-from-own-texts

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)

Hooks (2)

eventmatcherruns
UserPromptSubmit*bash narzedzia/przyrzady/karta_wnioskow.sh przy-prompcie >/dev/null 2>&1; exit 0
Stop*bash narzedzia/przyrzady/karta_wnioskow.sh wyslij --rzadko >/dev/null 2>&1; exit 0

Similar rigs

copied ✓