agentrigs
+ submit rig
~ / rigs / hirokisakabe / issuekit

hirokisakabe/issuekit

Agent Skills for issue-driven development.

↗ GitHub ★ 1 MIT updated 12d 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 hirokisakabe/issuekit/skills ./rig-issuekit/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 hirokisakabe/issuekit/skills/acceptance-check .claude/skills/acceptance-check
$ npx degit hirokisakabe/issuekit/skills/cross-review .claude/skills/cross-review
$ npx degit hirokisakabe/issuekit/skills/issue-create .claude/skills/issue-create
$ npx degit hirokisakabe/issuekit/skills/issue-discover .claude/skills/issue-discover
$ npx degit hirokisakabe/issuekit/skills/issue-dispatch .claude/skills/issue-dispatch
$ npx degit hirokisakabe/issuekit/skills/issue-implement .claude/skills/issue-implement
$ npx degit hirokisakabe/issuekit/skills/issue-investigate .claude/skills/issue-investigate
$ npx degit hirokisakabe/issuekit/skills/issue-pick .claude/skills/issue-pick
$ npx degit hirokisakabe/issuekit/skills/issue-refine .claude/skills/issue-refine
$ npx degit hirokisakabe/issuekit/skills/worktree-start .claude/skills/worktree-start

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 (10)

acceptance-checkcross-reviewissue-createissue-discoverissue-dispatchissue-implementissue-investigateissue-pickissue-refineworktree-start

Similar rigs

MysticalNobody/alatyr_flutter
A hardened Flutter starter and GitHub template for AI-agent development, with machine-enforced architecture, automated quality gates, and a Claude Code + Codex implementation/review workflow
★ 1 project Claude CodeCodex 2 skills 2 agents 2 hooks 1mo ago
Pragmatist 2.4k tok ·
cc-claws/cc-code
—
★ 5 project Claude Code 2 mcp 8 skills 3 agents 8d ago
Pragmatist 14.8k tok ·
MiaoDX/intuitive-flow
Shared config, skills, and update scripts for Claude Code, Codex. Not more custom and new skills, but combined best practices in the community.
★ 48 project Claude CodeCodex 14 skills 9d ago
Skill Collector 1.2k tok ·
alunduil/alunduil-chezmoi
Personal chezmoi-managed dotfiles and host config: bootstrap a fresh host from bare OS to a working setup in one command.
★ 2 setup Claude Code 14 skills today
Skill Collector 6.1k tok ·
copied ✓