agentrigs
+ submit rig
~ / rigs / heynicorivera / coding-agent-kit

heynicorivera/coding-agent-kit

No description.

↗ GitHub ★ 1 MIT updated today project Claude CodeCodexGemini CLI
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~696 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
2/5
Blocks destructive commands · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit heynicorivera/coding-agent-kit/.claude ./rig-coding-agent-kit  # 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.

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "permissions": {
    "deny": [
      "Edit(ops/verify.sh)",
      "Edit(ops/check-agent-kit.sh)",
      "Edit(ops/agent/**)",
      "Edit(.claude/settings.json)",
      "Edit(.codex/**)",
      "Edit(.cursor/hooks.json)",
      "Edit(.github/hooks/**)",
      "Edit(.github/workflows/**)",
      "Edit(.githooks/**)",
      "Edit(~/.cache/agent-kit/**)",
      "Bash(git commit *--no-verify*)",
      "Bash(git commit -n *)",
      "Bash(git config *core.hooksPath*)",
      "Bash(git -c *core.hooksPath*)",
      "Bash(rm *ops/*)",
      "Bash(mv *ops/*)",
      "Bash(chmod *ops/*)",
      "Bash(git rm *ops/*)",
      "Bash(git mv *ops/*)",
      "Bash(rm *.githooks*)",
      "Bash(chmod *.githooks*)"
    ]
  }
}

Hooks (3)

eventmatcherruns
SessionStartstartup|resume|clear|compact"$(git rev-parse --show-toplevel)"/ops/agent/session-start.sh
Stop*python3 "$(git rev-parse --show-toplevel)"/ops/agent/stop_gate.py --consumer claude
SessionEnd*"$(git rev-parse --show-toplevel)"/ops/agent/session-end.sh

Permissions

deny (21)
Edit(ops/verify.sh)
Edit(ops/check-agent-kit.sh)
Edit(ops/agent/**)
Edit(.claude/settings.json)
Edit(.codex/**)
Edit(.cursor/hooks.json)
Edit(.github/hooks/**)
Edit(.github/workflows/**)
Edit(.githooks/**)
Edit(~/.cache/agent-kit/**)
Bash(git commit *--no-verify*)
Bash(git commit -n *)
Bash(git config *core.hooksPath*)
Bash(git -c *core.hooksPath*)
Bash(rm *ops/*)
Bash(mv *ops/*)
Bash(chmod *ops/*)
Bash(git rm *ops/*)
Bash(git mv *ops/*)
Bash(rm *.githooks*)
Bash(chmod *.githooks*)
ask (0)
—
allow (0)
—

Similar rigs

multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
★ 217k collection Claude CodeCursor 1 skills 6mo ago
Minimalist 723 tok ·
shareAI-lab/learn-claude-code
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
★ 78.0k project Claude Code 4 skills 11d ago
Minimalist 156 tok ·
tt-a1i/archify
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
★ 76.3k project Claude CodeCodex 1 skills 7d ago
Minimalist 484 tok ·
ayghri/i-have-adhd
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
★ 53.7k project CodexCursorGemini CLI 1 skills 20d ago
Minimalist 1.4k tok ·
copied ✓