agentrigs
+ submit rig
~ / rigs / The-AIE / the-gibson

The-AIE/the-gibson

A portable, self-improving SDLC harness for agent fleets — plan → issues → build → test → review → UX-eval → security → ship, on any runtime (Claude Code, Codex, Grok, Hermes). Apache-2.0.

↗ GitHub ★ 40 apache-2.0 updated 6d ago project Claude CodeCodex
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~5.6k tokens
Moderate · 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 The-AIE/the-gibson/skills ./rig-the-gibson/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 The-AIE/the-gibson/.agents/skills/create-verification-skill .claude/skills/create-verification-skill
$ npx degit The-AIE/the-gibson/.agents/skills/maintain-verification-skill .claude/skills/maintain-verification-skill
$ npx degit The-AIE/the-gibson/.agents/skills/principle-prove-it-works .claude/skills/principle-prove-it-works
$ npx degit The-AIE/the-gibson/.agents/skills/principle-sequence-verifiable-units .claude/skills/principle-sequence-verifiable-units
$ npx degit The-AIE/the-gibson/.agents/skills/show-me-your-work .claude/skills/show-me-your-work
$ npx degit The-AIE/the-gibson/.agents/skills/testing-gibson-harness .claude/skills/testing-gibson-harness
$ npx degit The-AIE/the-gibson/skills/gibson-audit .claude/skills/gibson-audit
$ npx degit The-AIE/the-gibson/skills/gibson-direct .claude/skills/gibson-direct
$ npx degit The-AIE/the-gibson/skills/gibson-resources .claude/skills/gibson-resources
$ npx degit The-AIE/the-gibson/skills/gibson-run .claude/skills/gibson-run
$ npx degit The-AIE/the-gibson/skills/gibson-setup .claude/skills/gibson-setup
$ npx degit The-AIE/the-gibson/skills/gibson .claude/skills/gibson

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 (12)

create-verification-skillmaintain-verification-skillprinciple-prove-it-worksprinciple-sequence-verifiable-unitsshow-me-your-worktesting-gibson-harnessgibson-auditgibson-directgibson-resourcesgibson-rungibson-setupgibson

Similar rigs

itsvedantkumar/vstack
A Claude Code setup where the skills fire on their own: situation-routed skills, subagents, a session routing hook, and a verification gate whose every check is mutation-proven falsifiable. Installs global, per-repo overlay, or plugin marke
★ 5 setup Claude Code 29 skills 1mo ago
Skill Collector 2.1k tok ·
painhardcore/pstack
Portable coding-agent workflows adapted from Cursor’s pstack for Codex, Claude Code, and OpenCode.
★ 6 collection Codex 41 skills 1mo ago
Skill Collector 3.1k tok ·
cameronr/dotfiles
personal dotfiles
★ 30 setup Claude CodeCodex 44 skills 1d ago
Skill Collector 3.4k tok ·
peterpme/dotfiles
᠅ Dotfiles for zsh, tmux, fzf, neovim, git, zprezto, hammerspoon, kitty & more 🔥
★ 94 setup Claude Code 54 skills 1mo ago
Skill Collector 3.4k tok ·
copied ✓