claude

delegation

Typed read-only subagents (investigator, researcher, reviewer, skeptic), a guard-agent-type hook on catch-all subagent calls and the agents' Bash writes (off by default, log or block), and a measure of how sessions delegate to them: snapshots of a date window and a before/after compare

0 on GitHubby FunDrivenDevv0.4.0updated 2 days agoproductivity
/

Plugin delegation from marketplace fundrivendev in FunDrivenDev/claude-plugins. Commands read from the repo's manifest — 2 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (1)

  • measure

    Measure how sessions delegate to subagents and where the main session's context goes, as a snapshot of a date window (Markdown and JSON, aggregates only) or a before/after compare of two snapshots.

Subagents (4)

  • investigator

    Read-only diagnosis of a bug, a red test or check, a failed run or an odd behaviour, or a survey of a system's state. Reproduces it, reads code, logs and history, runs read-only commands, and returns the root cause tied to an observation at file:line. Brief it with the symptom, the command that show

  • researcher

    Read-only research on the web and in docs (a tool's or an API's behaviour, a version, a changelog, an option, the known causes of an error). Answers from primary sources, with their URLs. Brief it with the question, the version or date that matters, and what is already known. Use when only the answe

  • reviewer

    Read-only review of a diff, a branch, a PR or files for defects (correctness, a broken contract, a missed case, a breach of the repo's standards or of the spec in the brief), without the briefing session's reasoning. Returns verified findings only, each at file:line. Brief it with the base to diff a

  • skeptic

    Read-only adversary of a plan, a design, a decision or a claim. Tries to break it and returns the strongest objections that hold, each backed by evidence, or says that none hold. Brief it with the plan itself (or its path), the goal it serves, the constraints, and what was already weighed. Use befor

Hooks (1)

  • PreToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/guard_agent_type.py"

View source on GitHub

More from FunDrivenDev/claude-plugins

All 5 plugins →

handover

claude

Hand a session over to a fresh one before its context fills up: a separate model writes the handover from the transcript, /clear loads it

6 skills · hooks

0

tools

claude

Workflow tooling: wrap-up report (artifact, Bear, Slack), mental-model pages, MCP server audit, Claude config audit, local-LLM setup advice, and a hook that wakes a session waiting on a background task about once an hour for a one-line reply keeping the prompt cache warm (on by default, CACHE_KEEPALIVE=off to disable)

5 skills · hooks

0

statusline

claude

Deprecated: no longer maintained. Context-budget status line: tokens against the auto-compact trigger, prompt-cache countdown, quota pace, git branch and PR, plus plugin segments.

2 skills · hooks

0

session-mods

claude

A calm side pane (first prompt, sub-agents with their task and full history, a checklist of the session's steps) and a bar beneath the prompt (running time, prompt-cache countdown, context usage, quotas, and the model and effort selectors).

0

Similar plugins

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

pake

claudecodex

Package any website or local web build into a lightweight desktop app with Pake CLI.

1 skill

tw93/Pake 63,463

Maintain delegation?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins5 plugins