A

agentmemory-hooks

by @rohitg00v
4.5(120)

This skill automatically captures observations throughout an AI agent's session lifecycle, enabling automated memory management. It helps developers understand how memory is captured, debug missing observations, and fine-tune what gets recorded. This enhances the agent's autonomous learning and decision-making capabilities by ensuring comprehensive and accurate memory retention.

agent-memoryai-agentlifecycle-hooksobservation-capturememory-managementGitHub
Installation
npx skills add https://github.com/rohitg00/agentmemory --skill agentmemory-hooks
compare_arrows

Before / After Comparison

1
Before

Developers manually saved every agent observation or spent significant time debugging why an agent's memory was incomplete, leading to low development efficiency and difficulty in accurately tracing agent behavior.

After

This skill automatically captures all observation data throughout the agent's lifecycle, significantly reducing manual intervention. Developers can quickly pinpoint memory issues and optimize recording strategies, greatly improving debugging efficiency and the traceability of agent actions.

SKILL.md

The Claude Code plugin registers lifecycle hooks so memory is captured automatically. You do not have to call memory_save for routine work; the hooks observe tool use, prompts, and session boundaries and write observations for you.

Quick start

Install the plugin and the hooks register themselves:

/plugin marketplace add rohitg00/agentmemory
/plugin install agentmemory

Watch observations land live at http://localhost:3113.

What the hooks do

  • Session start and end frame each unit of work and let handoff resume it.
  • Tool-use hooks capture what changed and why, the raw material for recall and recap.
  • Prompt-submit captures intent. Pre-compact preserves context before the host trims it.
  • A post-commit hook links commits to sessions, which powers commit-context and commit-history.

Important

  • Capture is on by default and is zero-LLM. Turning observations into LLM summaries (AGENTMEMORY_AUTO_COMPRESS) and injecting them back into context (AGENTMEMORY_INJECT_CONTEXT) are separate opt-ins because they spend tokens.
  • If observations are missing, confirm the plugin is enabled and the server is running. See ../_shared/TROUBLESHOOTING.md.

See also

  • agentmemory-config for the capture and injection flags.
  • The handoff, recap, and session-history skills consume what these hooks record.

Reference

The exact registered hook events live in REFERENCE.md, generated from plugin/hooks/hooks.json.

User Reviews (0)

Write a Review

Effect
Usability
Docs
Compatibility

No reviews yet

Statistics

Installs9.2K
Rating4.5 / 5.0
Version
Updated2026年9月19日
Comparisons1

User Rating

4.5(120)
5
37%
4
43%
3
13%
2
5%
1
2%

Rate this Skill

0.0

Compatible Platforms

🤖claude-code

Timeline

Created2026年6月25日
Last Updated2026年9月19日
🎁 Agent Knowledge Cards
Survey