agentic-in/elephant-agent

Personal-Model First Self Evolving AI Agent 🐘

This repository also configures its own agents. See what elephant-agent tells them β†’

582Stars on the repository
93Mods indexed here, across every type
14d agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

LLM Wiki

73

agentic-in/elephant-agent

Skill Claude CodeCodex

Build concise, cross-linked wiki-style summaries for models, papers, techniques, or labs when the user wants durable knowledge capture.

not rated 582 14d ago A 29 tokens

Polymarket

74

agentic-in/elephant-agent

Skill Claude CodeCodex

Inspect prediction-market questions, prices, and resolution conditions carefully before summarizing or comparing market signals.

not rated 582 14d ago A 23 tokens

agentic-in/elephant-agent

Skill Claude CodeCodex

Draft research-style outlines, section structure, and evidence-backed prose for papers, whitepapers, or technical notes.

not rated 582 14d ago A 26 tokens

Shell Execution

76

agentic-in/elephant-agent

Skill Claude CodeCodex

Keeps explicit shell work legible, bounded, and attached to the current workspace thread.

not rated 582 14d ago A 21 tokens

Web Read

77

agentic-in/elephant-agent

Skill Claude CodeCodex

Keeps direct URL reading and text extraction available when a specific page matters more than search results.

not rated 582 14d ago A 22 tokens

Web Search

78

agentic-in/elephant-agent

Skill Claude CodeCodex

Keeps lightweight public-web discovery available for prompts, scheduled jobs, and follow-up research.

not rated 582 14d ago A 21 tokens

Workspace Search

79

agentic-in/elephant-agent

Skill Claude CodeCodex

Keeps local retrieval, file search, and nearby context gathering available in-session.

not rated 582 14d ago A 19 tokens

1Password

80

agentic-in/elephant-agent

Skill Claude CodeCodex

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in, and reading/injecting secrets for commands.

not rated 582 14d ago A 37 tokens

OSS Forensics

81

agentic-in/elephant-agent

Skill Claude CodeCodex

Investigate open-source supply-chain incidents with evidence collection, recovery, IOC tracking, and structured forensic reporting.

not rated 582 14d ago B 25 tokens

Sherlock

82

agentic-in/elephant-agent

Skill Claude CodeCodex

OSINT username search across 400+ social networks. Hunt down social media accounts by username.

not rated 582 14d ago A 22 tokens

OpenHue

83

agentic-in/elephant-agent

Skill Claude CodeCodex

Control Philips Hue lights, rooms, and scenes from the terminal through the OpenHue CLI with explicit targeting and safe defaults.

not rated 582 14d ago A 27 tokens

Xitter

84

agentic-in/elephant-agent

Skill Claude CodeCodex

Interact with X/Twitter through an official-API CLI flow for search, timelines, mentions, and carefully confirmed posting actions.

not rated 582 14d ago A 28 tokens

Plan

85

agentic-in/elephant-agent

Skill Claude CodeCodex

Break ambiguous work into explicit, verifiable steps before implementation when the task is broad enough to benefit from a plan.

not rated 582 14d ago A 25 tokens

agentic-in/elephant-agent

Skill Claude CodeCodex

Package a code change for review with clear scope, risk notes, and validation evidence so reviewers can move quickly.

not rated 582 14d ago A 27 tokens

Skill Creator

87

agentic-in/elephant-agent

Skill Claude CodeCodex

Guide for creating effective Elephant Agent skills. Use this skill when users want to create a new skill or update an existing skill that extends Elephant Agent with specialized knowledge, workflows, or tool integrations.

not rated 582 14d ago A 41 tokens

agentic-in/elephant-agent

Skill Claude CodeCodex

Split work into parallelizable, bounded tracks only when the tasks have disjoint ownership and the coordination cost is justified.

not rated 582 14d ago A 28 tokens

agentic-in/elephant-agent

Skill Claude CodeCodex

Investigate bugs by reproducing, isolating, and validating a root-cause hypothesis before applying fixes.

not rated 582 14d ago A 26 tokens

agentic-in/elephant-agent

Skill Claude CodeCodex

Drive behavior changes through a failing test, the smallest working implementation, and then cleanup once the behavior is locked.

not rated 582 14d ago A 26 tokens

Writing Plans

91

agentic-in/elephant-agent

Skill Claude CodeCodex

Write execution plans that preserve intent, scope, dependencies, and validation without turning into vague prose.

not rated 582 14d ago A 22 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page β€” the rest are on their repository pages: