bhaveshpabnani/humungousaur/claude-code-delegation

Claude Code and agent skill by bhaveshpabnani/humungousaur

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Plan Claude Code delegation only when a native, approved adapter exists; otherwise prepare a handoff brief and report the missing implementation gap.

Install

npx vskill@latest install bhaveshpabnani/humungousaur/claude-code-delegation

SKILL.md

Claude Code Delegation

Purpose

Represent Claude Code as a possible coding worker without pretending it is integrated. Humungousaur must use an owned adapter before executing Claude Code tasks.

When To Use

Use when the user asks to use Claude Code, compare coding workers, or prepare a Claude-oriented handoff.

Inputs And Evidence

  • Task objective, repo path, constraints, tests, and desired sandbox.
  • Capability search showing whether a native Claude Code adapter exists.
  • Handoff prompt or missing-adapter report.

Tool Map

  • tool_search
  • capability_surface
  • write_note
  • codex_cli_plan
  • coding-agent

Workflow

  1. Check whether Humungousaur exposes a native Claude Code tool or configured adapter.
  2. If missing, say the adapter is not implemented and prepare a reusable handoff brief.
  3. If implemented later, require approval and bounded sandbox execution.
  4. Verify any delegated output locally.
  5. Prefer existing codex_cli_* delegation when the user accepts Codex as the worker.

Native Implementation Boundaries

  • Do not call Claude Code CLI directly unless a Humungousaur-owned adapter/tool exists or the user explicitly requests an approved shell action.
  • Do not import external reference Claude Code scripts.
  • Do not treat external installation as native integration.

Safety And Approval

  • Delegated coding tools can modify files; require approval and scoped workdirs.
  • Do not pass secrets.
  • Preserve dirty worktrees.

Verification

  • Capability status must prove whether native support exists.
  • Handoff briefs are drafts, not executed work.
  • Any executed result needs local verification.

Failure Modes

  • Claiming Claude Code ran when only a prompt was drafted.
  • Delegating too much context.
  • Skipping local verification.

References

  • Shortlist item: claude-code-delegation.
  • Upstream inspiration: external reference Claude Code references only.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
8
7-day trend score
16

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/bhaveshpabnani/humungousaur/claude-code-delegation/badge)](https://verified-skill.com/skills/bhaveshpabnani/humungousaur/claude-code-delegation)

Something wrong with this skill or its page? Tell us.