agentrigs
+ submit rig
~ / rigs / dzhng / jevgrep

dzhng/jevgrep

Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.

↗ GitHub ★ 2 mit updated 13d ago project Codex
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~3.5k 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 dzhng/jevgrep/skills ./rig-jevgrep/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 dzhng/jevgrep/.agents/skills/audit-agents .claude/skills/audit-agents
$ npx degit dzhng/jevgrep/.agents/skills/audit-choices .claude/skills/audit-choices
$ npx degit dzhng/jevgrep/.agents/skills/audit-performance .claude/skills/audit-performance
$ npx degit dzhng/jevgrep/.agents/skills/audit-tests .claude/skills/audit-tests
$ npx degit dzhng/jevgrep/.agents/skills/auto-research .claude/skills/auto-research
$ npx degit dzhng/jevgrep/.agents/skills/close-spec .claude/skills/close-spec
$ npx degit dzhng/jevgrep/.agents/skills/code-review .claude/skills/code-review
$ npx degit dzhng/jevgrep/.agents/skills/codex .claude/skills/codex
$ npx degit dzhng/jevgrep/.agents/skills/compare-screenshots .claude/skills/compare-screenshots
$ npx degit dzhng/jevgrep/.agents/skills/design-with-images .claude/skills/design-with-images
$ npx degit dzhng/jevgrep/.agents/skills/eli5 .claude/skills/eli5
$ npx degit dzhng/jevgrep/.agents/skills/eval-skills .claude/skills/eval-skills
$ npx degit dzhng/jevgrep/.agents/skills/explore-unknowns .claude/skills/explore-unknowns
$ npx degit dzhng/jevgrep/.agents/skills/handoff-spec .claude/skills/handoff-spec
$ npx degit dzhng/jevgrep/.agents/skills/implement-spec-with-codex .claude/skills/implement-spec-with-codex
$ npx degit dzhng/jevgrep/.agents/skills/implement-spec .claude/skills/implement-spec
$ npx degit dzhng/jevgrep/.agents/skills/jevgrep .claude/skills/jevgrep
$ npx degit dzhng/jevgrep/.agents/skills/launch-video .claude/skills/launch-video
$ npx degit dzhng/jevgrep/.agents/skills/marketing-pages .claude/skills/marketing-pages
$ npx degit dzhng/jevgrep/.agents/skills/preview-shots .claude/skills/preview-shots
$ npx degit dzhng/jevgrep/.agents/skills/refactor-clean .claude/skills/refactor-clean
$ npx degit dzhng/jevgrep/.agents/skills/review .claude/skills/review
$ npx degit dzhng/jevgrep/.agents/skills/screenshot-critique .claude/skills/screenshot-critique
$ npx degit dzhng/jevgrep/.agents/skills/typesafe-ai .claude/skills/typesafe-ai
$ npx degit dzhng/jevgrep/.agents/skills/write-docs .claude/skills/write-docs
$ npx degit dzhng/jevgrep/.agents/skills/write-skills .claude/skills/write-skills
$ npx degit dzhng/jevgrep/.agents/skills/write-spec .claude/skills/write-spec
$ npx degit dzhng/jevgrep/.agents/skills/write-tests .claude/skills/write-tests

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 (28)

audit-agentsaudit-choicesaudit-performanceaudit-testsauto-researchclose-speccode-reviewcodexcompare-screenshotsdesign-with-imageseli5eval-skillsexplore-unknownshandoff-specimplement-spec-with-codeximplement-specjevgreplaunch-videomarketing-pagespreview-shotsrefactor-cleanreviewscreenshot-critiquetypesafe-aiwrite-docswrite-skillswrite-specwrite-tests

Similar rigs

justxor/claude-code-pro-course
Claude Code PRO — полный курс и гайд на русском: CLAUDE.md, settings, skills, subagents, hooks, MCP, плагины, CI. 8 лабораторных, библиотека промптов и готовый starter-kit. Здесь бесплатные курсы по chatgpt -
★ 133 project Claude Code 2 mcp 9 skills 5 agents 4 hooks 8d ago
Fort Knox 27.4k tok ·
azharuddinkhan8898/ai-core
Centralized AI registry and distribution system for reusable AI assets — skills, instructions, agents, and MCP configs — across coding agents like GitHub Copilot, Claude Code, Cursor, and Windsurf.
★ 0 project Claude Code 7 skills 4mo ago
Pragmatist 408 tok ·
tdiprima/claude-config
Claude Code dotfiles and bootstrap script to configure a new machine with rules, skills, and settings in one command.
★ 0 setup Claude Code 7 skills 13d ago
Pragmatist 686 tok ·
heliohq/ship
An agentic development harness for Claude Code, Codex & Cursor: gated pipeline from spec to green checks.
★ 82 project Codex 1 mcp 10 skills 3mo ago
Skill Collector 3.7k tok ·
copied ✓