Is the Agentlog skill free?

Yes. The skill itself is free from Yrzhe/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agentlog SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Agentlog?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Agentlog with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Agentlog

Real, working CLI that pools Claude Code/Codex/Cursor/Maestri activity across devices via a git-synced pool.

by Yrzhe · Yrzhe/claude-skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 2ea396b

This is not a prompt-only skill -- ran the real CLI end to end (init against a throwaway git remote, event push, pool, recap, push) and it all worked exactly as documented; the bundled pytest suite passed 59/59, matching the README's '59 passing' claim to the digit.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Agentlog does

A genuine Python CLI (not just a prompt) that captures agent-session events from multiple tools and machines into one normalized, deduped JSONL pool synced through a git remote, then serves recap/pool views and distills per-project AGENTS.md/CLAUDE.md context. Triggers on cross-device 'what did I do today across my agents' and context-handoff requests; explicitly excludes single-machine tweet capture (seed) and one-off planning.

How to install Agentlog

git clone https://github.com/Yrzhe/claude-skills.git
cd claude-skills
mkdir -p ~/.claude/skills
cp -r plugins/agentlog ~/.claude/skills/agentlog

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agentlog

/agentlog Real, working CLI that pools Claude Code/Codex/Cursor/Maestri activity across devices via a git-synced pool.

It also activates on plain-language prompts like these:

What did I work on today across Claude Code, Cursor, and Codex?
Pool my agent session logs from all my devices into one recap
Distill our project's session history into an updated AGENTS.md file

Frequently asked questions

Is the Agentlog skill free?: Yes. The skill itself is free from Yrzhe/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agentlog work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. This is not a prompt-only skill -- ran the real CLI end to end (init against a throwaway git remote, event push, pool, recap, push) and it all worked exactly as documented; the bundled pytest suite passed 59/59, matching the README's '59 passing' claim to the digit.
What is the Agentlog SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Agentlog?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agentlog with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.