agentrigs
+ submit rig
~ / rigs / Fergius-Engineering / instincts

Fergius-Engineering/instincts

Working-instinct skills for Claude Code: verify claims against the source, log for the bug you can't reproduce, write like a human, test so the test bites. A reflex layer on top of superpowers.

↗ GitHub ★ 2 MIT updated 2mo ago project Claude Code Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~823 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit Fergius-Engineering/instincts/skills ./rig-instincts/skills

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 Fergius-Engineering/instincts/skills/build-release-mindset .claude/skills/build-release-mindset
$ npx degit Fergius-Engineering/instincts/skills/critical-thinking .claude/skills/critical-thinking
$ npx degit Fergius-Engineering/instincts/skills/de-ai-prose .claude/skills/de-ai-prose
$ npx degit Fergius-Engineering/instincts/skills/entry-point-audit .claude/skills/entry-point-audit
$ npx degit Fergius-Engineering/instincts/skills/feasibility-guard .claude/skills/feasibility-guard
$ npx degit Fergius-Engineering/instincts/skills/fix-in-the-shared-layer .claude/skills/fix-in-the-shared-layer
$ npx degit Fergius-Engineering/instincts/skills/fix-the-root-cause .claude/skills/fix-the-root-cause
$ npx degit Fergius-Engineering/instincts/skills/independent-review-gate .claude/skills/independent-review-gate
$ npx degit Fergius-Engineering/instincts/skills/logging-for-remote-diagnosis .claude/skills/logging-for-remote-diagnosis
$ npx degit Fergius-Engineering/instincts/skills/no-duplicate-logic .claude/skills/no-duplicate-logic
$ npx degit Fergius-Engineering/instincts/skills/opportunistic-fixes .claude/skills/opportunistic-fixes
$ npx degit Fergius-Engineering/instincts/skills/performance-at-scale .claude/skills/performance-at-scale
$ npx degit Fergius-Engineering/instincts/skills/plan-with-teeth .claude/skills/plan-with-teeth
$ npx degit Fergius-Engineering/instincts/skills/project-onto-all-systems .claude/skills/project-onto-all-systems
$ npx degit Fergius-Engineering/instincts/skills/question-the-premise .claude/skills/question-the-premise
$ npx degit Fergius-Engineering/instincts/skills/tests-with-teeth .claude/skills/tests-with-teeth
$ npx degit Fergius-Engineering/instincts/skills/user-action-edge-cases .claude/skills/user-action-edge-cases
$ npx degit Fergius-Engineering/instincts/skills/using-instincts .claude/skills/using-instincts
$ npx degit Fergius-Engineering/instincts/skills/ux-designer-mindset .claude/skills/ux-designer-mindset
$ npx degit Fergius-Engineering/instincts/skills/verify-against-code .claude/skills/verify-against-code

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 (20)

build-release-mindsetcritical-thinkingde-ai-proseentry-point-auditfeasibility-guardfix-in-the-shared-layerfix-the-root-causeindependent-review-gatelogging-for-remote-diagnosisno-duplicate-logicopportunistic-fixesperformance-at-scaleplan-with-teethproject-onto-all-systemsquestion-the-premisetests-with-teethuser-action-edge-casesusing-instinctsux-designer-mindsetverify-against-code

Similar rigs

tronghieu/agent-skills
Method-driven agent skills for knowledge work: strategy, research, critical thinking, data analysis, docs, slides. Works with Claude Code, Codex, Cursor and any agentskills.io-compatible agent.
★ 72 collection Claude CodeCodex 19 skills 9d ago
Skill Collector 1.9k tok ·
obra/superpowers
An agentic skills framework & software development methodology that works.
★ 294k project CodexGemini CLI 15 skills 12d ago
Skill Collector 3.0k tok ·
anthropics/skills
Public repository for Agent Skills
★ 180k collection Claude Code 19 skills 4d ago
Skill Collector 1.3k tok ·
anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
★ 149k project Claude Code 10 skills 6d ago
Skill Collector 1.4k tok ·
copied ✓