What is agent-gep-lite?

An experience layer that recalls proven lessons before tasks are assigned and saves the results after review. It stores reusable guidance in local files that can travel with the Git repository.

It helps enrich task briefs with relevant experience and record whether completed work passed or failed review.

It lets future tasks benefit from earlier successes and avoid documented failure patterns.

agent-gep-lite — Plugin for Claude Code by wu736139669: An experience layer that recalls proven lessons before tasks…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add wu736139669/agent-taskgraph-protocol

agentmods

npx agentmods add plugins/wu736139669/agent-taskgraph-protocol/agent-gep-lite

Clone the repo

git clone --depth 1 https://github.com/wu736139669/agent-taskgraph-protocol

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/wu736139669/agent-taskgraph-protocol/agent-gep-lite.svg)](https://agentmods.dev/plugins/wu736139669/agent-taskgraph-protocol/agent-gep-lite)

Your own site

<a href="https://agentmods.dev/plugins/wu736139669/agent-taskgraph-protocol/agent-gep-lite"><img src="https://agentmods.dev/badge/plugins/wu736139669/agent-taskgraph-protocol/agent-gep-lite.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 skill cost 91 tokens a session between them.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

agent-gep-lite scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/agent-gep-lite/.claude-plugin/plugin.json · 19 lines

What it actually says

{
  "name": "agent-gep-lite",
  "description": "GEP-lite experience layer: recall proven Genes/Capsules before dispatch, solidify validation results after acceptance.",
  "version": "0.1.0",
  "author": {
    "name": "wu736139669"
  },
  "homepage": "https://github.com/wu736139669/agent-taskgraph-protocol",
  "repository": "https://github.com/wu736139669/agent-taskgraph-protocol",
  "license": "Apache-2.0",
  "keywords": [
    "ai-coding",
    "self-evolution",
    "experience-reuse",
    "memory",
    "agent-orchestration"
  ]
}

Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 91 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Skill agent-gep-lite A 91 tokens

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today First seen · 19 lines scan A 0ad3054d4540

Subscribe to this mod's changes

agent-gep-lite is a plugin published in the GitHub repository wu736139669/agent-taskgraph-protocol (4 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Building agents Memory and context Multi-Agent Orchestration ai-agents claude-code codex coding-agent

pilotfish

macOS and Linux Claude Code Plugin beta with hook-based ambient policy activation and namespaced role agents.

Nanako0129/pilotfish · not measured

gaia-marketplace

Security-first multi-agent orchestration for Claude Code. Distributes the Gaia plugin: specialized agents across the development lifecycle with codebase-aware context injection and risk-classified command gating.

metraton/gaia · not measured

open-magi

Magi proposal-first multi-agent deliberation loop for Claude Code.

ladiossoop5star/open_magi · not measured

ac

Main-agent planning trio (/ac:plan, /ac:execute, /ac:wisdom) with autonomous execution mode plus setup, init, commit commands and skill, agent, command, rule, CLAUDE.md creator skills. Two hooks back the workflow: SessionStart for twin-skill and resume, PreCompact for state preservation.

anilcancakir/claude-code-plugin · not measured

git-master

Git expert skill — atomic commits, interactive rebase, and history archaeology for Claude Code.