~ / rigs / dongnguyenvie / bashcut-agent-kit

dongnguyenvie/bashcut-agent-kit

BashCut's agent kit: editing skills (footage survey, beat cuts, audio mix, captions, colour, voiceover…) and the BashCut MCP server for Claude Code and Codex.

↗ GitHub ★ 5 MIT updated 1mo ago project Claude Code Claude plugin
stack: Python
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
up to ~4.1k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 0/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit dongnguyenvie/bashcut-agent-kit/agents ./rig-bashcut-agent-kit/agents
$ npx degit dongnguyenvie/bashcut-agent-kit/skills ./rig-bashcut-agent-kit/skills
$ npx degit dongnguyenvie/bashcut-agent-kit/hooks ./rig-bashcut-agent-kit/hooks

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 dongnguyenvie/bashcut-agent-kit/skills/audio-mix .claude/skills/audio-mix
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/beat-cut .claude/skills/beat-cut
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/captions-text .claude/skills/captions-text
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/color-grade .claude/skills/color-grade
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/edit-workflow .claude/skills/edit-workflow
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/effects .claude/skills/effects
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/footage-survey .claude/skills/footage-survey
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/library .claude/skills/library
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/motion-graphics .claude/skills/motion-graphics
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/review .claude/skills/review
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/rough-cut .claude/skills/rough-cut
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/self-learn .claude/skills/self-learn
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/setup .claude/skills/setup
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/stock-images .claude/skills/stock-images
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/style-study .claude/skills/style-study
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/visual-plan .claude/skills/visual-plan
$ npx degit dongnguyenvie/bashcut-agent-kit/skills/voiceover .claude/skills/voiceover
$ curl -fsSL --create-dirs -o .claude/agents/critic.md https://raw.githubusercontent.com/dongnguyenvie/bashcut-agent-kit/main/agents/critic.md
$ curl -fsSL --create-dirs -o .claude/agents/surveyor.md https://raw.githubusercontent.com/dongnguyenvie/bashcut-agent-kit/main/agents/surveyor.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(git push --force:*)",
      "Read(**/*.pem)",
      "Read(.env)",
      "Read(~/.aws/**)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Bash(rm -rf *)",
      "Bash(sudo *)",
      "Bash(sudo:*)",
      "Bash(rm -rf /)",
      "Bash(git push -f:*)",
      "Read(.env.*)",
      "Bash(git reset --hard*)",
      "Bash(rm -rf /*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(gh pr merge *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(gh pr merge:*)",
      "Bash(gh pr create *)",
      "Bash(git reset --hard:*)",
      "Bash(npm publish:*)",
      "Bash(git rebase *)"
    ]
  }
}

MCP servers (1)

serversourceest. tokens
bashcut local / custom 2.5k

Skills (17)

Subagents (2)

critic
model: sonnet
Independent critic of a BashCut edit: judges a review packet as a viewer, measures text before calling it unreadable, and returns a verdict with findings and their fixes as one plan.cut patch in under
surveyor
model: sonnet
Surveys footage for a BashCut edit: reads the whole digest and transcript, looks at contact sheets, stores shot descriptions and returns hook candidates, exact quotes with times and angles in under 45

Similar rigs

copied ✓