Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

agentmemory-hooks — Claude Code skill: capture and setup

This skill explains how agentmemory hooks record observations during an agent session. Use it to understand what gets captured or troubleshoot missing observations.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add rohitg00/agentmemory --skill agentmemory-hooks -a claude-code
Open on GitHub

What agentmemory-hooks does

The hooks mark session starts and ends, capture tool use and submitted prompts, and preserve context before it is compacted. A post-commit hook links commits to sessions. The resulting observations feed recall, recap, commit-context, and commit-history.

Routine work does not require a manual memory_save call. Hooks capture observations by default without an LLM; summary generation through AGENTMEMORY_AUTO_COMPRESS and context injection through AGENTMEMORY_INJECT_CONTEXT are separate settings. Check the host configuration, since native integrations have their own capture and recall settings.

If observations are missing, check that the plugin is enabled and the server is running. In Claude Code, the plugin setup uses marketplace commands; Devin plugin hooks run only in local sessions. This skill is not user-invocable.

What it helps with

  • capture session observations without calling memory_save
  • preserve context before compaction
  • link commits to agent sessions
  • troubleshoot missing observations

Example prompts for the agent

  • Explain which session events agentmemory-hooks records.
  • Help me troubleshoot why agentmemory observations are missing.
  • Compare the roles of `AGENTMEMORY_AUTO_COMPRESS` and `AGENTMEMORY_INJECT_CONTEXT`.

How to install agentmemory-hooks

1Skills CLI (Vercel)

npx skills add rohitg00/agentmemory --skill agentmemory-hooks -a claude-code

2Manually: put the files in place

~/.claude/skills/agentmemory-hooks/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/agentmemory-hooks/

From the same set11

The whole set →
remember rohitg00 Saves insights, decisions, and learnings to agentmemory long-term storage with concept tags so agents can retrieve them later. Claude Code CX Codex Cursor +1 14,000installs recall rohitg00 Searches past observations, sessions, and learnings through agentmemory. Use it to recover context when you need to know what a project already covered. Claude Code CX Codex Cursor +1 13,900installs forget rohitg00 Deletes selected durable memories from agentmemory after explicit confirmation. Useful when scrubbing secrets or obsolete notes. Claude Code CX Codex Cursor +1 13,800installs session-history rohitg00 Shows recent project sessions as a clean timeline. Use it to recover past decisions, observations, and session status. Claude Code CX Codex Cursor +1 13,800installs commit-history rohitg00 Lists git commits linked to agent sessions with optional filters for branch, repo, and limit. Claude Code CX Codex Cursor +1 13,700installs handoff rohitg00 Resumes the latest agent session for the current directory and surfaces any unanswered questions first. Claude Code CX Codex Cursor +1 13,400installs agentmemory-agents rohitg00 Guides coding agents on linking the memory server via agentmemory connect. It safely merges host configurations without wiping existing MCP servers. Claude Code CX Codex Cursor +1 11,000installs agentmemory-mcp-tools rohitg00 Index of every agentmemory MCP tool with its parameters and workflows. Helps agents pick the right memory tool and format valid arguments. Claude Code CX Codex Cursor +1 10,900installs

Similar

flags react This skill runs React's feature-flag command and explains the results. Use it to compare release channels when a feature behaves differently between them. Claude Code CX Codex Cursor +1 1,100installs flow react Runs Flow type checking in a React project and reports errors with file locations. Useful when you edit code and don't want to look up the right renderer flag each time. Claude Code CX Codex Cursor +1 1,100installs task-management official anthropics Tracks commitments, active work, and follow-ups in a local TASKS.md file. Useful when managing project to-dos directly from the AI coding chat. Claude Code CX Codex Cursor +1 7,200installs security-ownership-map official openai Builds a people-to-file map from git history, computes bus factor, and flags sensitive code with too few active owners. Claude Code CX Codex Cursor +1 3,800installs weekly-digests thedotmack Splits a claude-mem timeline into per-ISO-week files and produces one narrative chapter per week. Use it when you want a serial story, not a single report. Claude Code CX Codex Cursor +1 4,000installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. Claude Code CX Codex 282,859installs

Questions about agentmemory-hooks

How do I install agentmemory-hooks in Codex?

Run npx skills add rohitg00/agentmemory --skill agentmemory-hooks -a codex. The skill file is at .agents/skills/agentmemory-hooks/SKILL.md.

What does agentmemory-hooks do?

It records observations about sessions, tool use, and prompts. A post-commit hook links commits to their sessions.

Does observation capture require an LLM?

No. Hooks capture observations by default without an LLM. Summary generation and context injection use separate settings.

Source text

SKILL.md · Apache-2.0 
---
name: agentmemory-hooks
description: The agentmemory plugin hooks that capture observations automatically across the agent session lifecycle. Use when explaining how memory gets captured without manual saves, when debugging missing observations, or when tuning what gets recorded.
user-invocable: false
---

The agentmemory 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

For Claude Code, install its plugin:

```bash
/plugin marketplace add rohitg00/agentmemory
/plugin install agentmemory
```

For Devin CLI and Devin Desktop, install the plugin and start a new session:

```bash
devin plugins install rohitg00/agentmemory#plugin
```

Run `/hooks` inside Devin to confirm the agentmemory hooks are loaded. Plugin hooks run only in local Devin sessions, not in cloud sessions.

Hermes and OpenClaw use their native integrations and lifecycle contracts. Follow the matching integration setup instructions and verify a real turn creates an observation. Installing shared skills or connecting MCP alone does not enable automatic capture. Watch recorded observations in the viewer at `http://localhost:3113` when using the default port.

## 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

- The plugin hooks capture by default without an LLM. Summary generation (`AGENTMEMORY_AUTO_COMPRESS`) and hook context injection (`AGENTMEMORY_INJECT_CONTEXT`) are separate options. Native integrations have their own recall/capture settings; inspect the host configuration instead of assuming these flags control every plugin.
- If observations are missing, confirm the plugin is enabled and the server is running. See [TROUBLESHOOTING.md](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`.

© rohitg00 · Apache-2.0 · rohitg00/agentmemory

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor