Skillget

agent-framework

agent
Guvenlik Denetimi
Uyari
Health Uyari
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 9 GitHub stars
Code Gecti
  • Code scan — Scanned 5 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This is a Claude Code plugin that provides compact "skills" to orchestrate sub-agents, run tasks in parallel, and improve one-shot task completion with minimal prompt overhead.

Security Assessment
The automated code scan of five files found no dangerous patterns, hardcoded secrets, or excessive permissions. However, the tool's own capabilities are inherently high-risk: several skills dispatch shell commands (agentify, automate), start local API servers (provideme), or orchestrate headless browser automation (web). The `automate` skill also integrates with Telegram, requiring careful handling of API keys. Because these skills are designed to execute code and interact with external services on your machine, overall risk is rated Medium. The underlying framework is safe, but the automated workflows it enables require careful review before execution.

Quality Assessment
The project is very new and has low visibility, currently sitting at only 9 GitHub stars. That said, it was updated very recently (last push was today), indicating active, ongoing development. It is properly licensed under the permissive Apache-2.0 license. Community trust and battle-testing are currently minimal due to the low adoption rate.

Verdict
Use with caution. The code itself is clean and open-source, but always inspect individual skill files before allowing them to execute commands, spawn servers, or access external networks on your system.
SUMMARY

Claude Code plugin containing high-leverage per token skills for agentic workflows.

README.md

Agent Workflow Amplifiers

A Claude Code plugin of high-leverage skills that improve orchestration, integration, and one-shot task completion with minimal prompt overhead.

What This Is

This repo contains compact skills for agentic workflows.

These skills are not meant to add net-new intelligence. They are meant to extract more value from capabilities the agent already has — planning, execution, sub-agents, validation, and tool use.

The goal is simple: small prompts, disproportionate workflow improvement.

Core Idea

A good skill is not just a reminder. It should do one of three things:

  • act as a force multiplier by unlocking more of the agent's existing capabilities
  • improve one-shot completion by increasing the odds a large task is fully completed in one pass
  • do both

This repo is focused on high leverage per token.

Included Skills & Agents

Every skill is a single SKILL.md. The description field controls when Claude auto-invokes it — see each file for the full body.

Skills

Skill What it does
agentify Bootstraps a dispatchable sub-agent skill for every coding agent CLI installed on the machine (codex, aider, cursor, etc.).
appmap Maps a web UI and generates a Claude skill to automate it via parallel orchestration.
automate Sets up a cron/launchd job to run Claude headlessly and send results to Telegram.
contract Reference convention for sub-agent I/O schemas. Preloaded into orchestrator agents via their skills: field — not directly invoked.
forge Autonomously grows the plugin: identifies gaps, generates a new amplifier, creates it, and validates through the qualify gate. Experimental.
integrate One-prompt API integration pipeline. Any API (docs URL, name, or description) → working CLI wrapper + skill + tests.
parallelize Transforms a linear plan into a dependency-aware orchestration plan for waves of parallel sub-agents. Run after /plan.
provideme One-prompt provider bridge. Any coding agent CLI → local Anthropic-compatible API server (POST /v1/messages) with a {provider}-claude launcher.
research Dispatches two sub-agents in parallel — one to search the web, one to inspect the local codebase — and returns a merged research brief.
resolve Resolves PR code review feedback by dispatching one parallel sub-agent per issue.
spec Transforms a loose idea into a structured, actionable spec ready for implementation.
web Orchestrates parallel browser automation across independent Chrome tabs, one sub-agent per tab.

Agents

Agent What it does
qualify Gate-keeps proposed skills. Approves only real force multipliers; rejects reminders, checklists, and best-practice nudges. Used by forge and available standalone.

Installation

From the marketplace

Inside a Claude Code session:

/plugin marketplace add griffinwork40/agent-framework
/plugin install agent-workflow-amplifiers@griffinwork40-agent-framework
/reload-plugins

Local installation

git clone https://github.com/griffinwork40/agent-framework.git
claude --plugin-dir ./agent-framework

Requires Claude Code v1.0.33 or later.

Usage

Examples:

  • After planning, run /parallelize to restructure the work into concurrent waves.
  • /integrate stripe — read Stripe's docs, produce a CLI wrapper + skill + tests.
  • /research — before starting a task, get web + codebase context in one shot.
  • /spec "idea in one sentence" — turn an idea into a scoped plan.
  • /qualify — evaluate a proposed skill before adding it.

What Qualifies as a Skill

A skill belongs in this repo only if it does at least one of:

  • changes the shape of the workflow (adds phases, parallelism, sub-agent dispatch)
  • unlocks more of the agent's existing capabilities
  • materially improves one-shot task completion
  • creates a repeatable workflow upgrade the base agent wouldn't reliably apply by default

Useful behaviors like validation, review, or TDD may still matter, but they are usually not strong enough to deserve first-class status on their own. The qualify agent enforces this bar — see agents/qualify.md for the rubric.

Contributing

See CONTRIBUTING.md. New skills are expected to pass the qualify gate before submission.

License

Apache 2.0 — see LICENSE.

Yorumlar (0)

Sonuc bulunamadi