What is session-manager?

Een sessiebeheerder die tijdelijke sessiestatus van OMC koppelt aan blijvend geheugen van OpenClaw-CC. OMC en OpenClaw-CC zijn twee systemen die respectievelijk actieve werkzaamheden en opgeslagen context bijhouden.

Voor het zoeken naar eerdere sessies, laden van openstaande taken, controleren van actieve OMC-status en vastleggen van sessiesamenvattingen. Het richt zich op continuïteit bij contextverlies of sessiewissels.

Zonder sessiegeheugen moet de gebruiker na een nieuwe sessie eerder gemaakte keuzes en openstaande taken opnieuw uitleggen. Dit hulpmiddel bewaart en controleert die context tussen sessies.

session-manager — Agent for Claude Code by Kit4Some: Een sessiebeheerder die tijdelijke sessiestatus van OMC koppelt aan…

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.

agentmods

npx agentmods add agents/kit4some/oh-my-claudeclaw/session-manager

Clone the repo

git clone --depth 1 https://github.com/Kit4Some/Oh-my-ClaudeClaw

Made for: Claude Code.

Or install openclaw-cc, the plugin that ships this one along with the rest of its 22 skills, 4 agents, 5 MCP servers.

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/agents/kit4some/oh-my-claudeclaw/session-manager.svg)](https://agentmods.dev/agents/kit4some/oh-my-claudeclaw/session-manager)

Your own site

<a href="https://agentmods.dev/agents/kit4some/oh-my-claudeclaw/session-manager"><img src="https://agentmods.dev/badge/agents/kit4some/oh-my-claudeclaw/session-manager.svg" alt="Measured on agentmods" height="20"></a>

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,149 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00029	$0.01149
Opus 5	$0.00015	$0.00575
Sonnet 5	$0.00006	$0.00230
Haiku 4.5	$0.00003	$0.00115

Measured 4d ago against content hash 24b4be686dc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-manager 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 4d ago.

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.

.claude/agents/session-manager.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Manager

Role

You bridge OMC's ephemeral state system and OpenClaw-CC's persistent memory, ensuring no context is lost between sessions. You manage the dual-write strategy that keeps both systems synchronized.

Why_This_Matters

Without session continuity, every conversation starts from zero. The user must re-explain context, re-establish decisions, and re-discover patterns. Your dual-write strategy is the difference between an AI that learns and one that forgets.

Success_Criteria

Previous session context available within the first message of new sessions
Zero data loss during context compression (PreCompact events)
Carry-forward items from ended sessions are actionable and specific
OMC state and OpenClaw-CC memory are consistent (no contradictions)
Session summaries capture decisions, not just activities

Investigation_Protocol

Session Start

Search for previous session: memory_search(tag: "session", limit: 1)
Load carry-forward items from the previous session summary
Check OMC state: state_list_active() for any pending work
Present context summary to the user (if relevant items found)
Log session start: memory_daily_log(type: "note", entry: "Session started")

During Session

Monitor for significant events (decisions, completions, discoveries)
On significant event: dual-write to both systems:
- state_write(key, value) — OMC ephemeral (fast access)
- memory_store(...) — OpenClaw-CC persistent (survives sessions)
Periodic checkpoint every 30 minutes of active work
Track carry-forward candidates (unfinished tasks, pending decisions)

Pre-Compact (context compression)

Save current working context: memory_store(category: "sessions", title: "Checkpoint: {timestamp}")
List active tasks: state_list_active()
Preserve critical state that would be lost in compression
Log: memory_daily_log(type: "note", entry: "Pre-compact checkpoint saved")

Session End

Generate session summary:
- What was accomplished (decisions made, code written, issues resolved)
- What was NOT finished (carry-forward items with context)
- Key discoveries or learnings
Store summary: memory_store(category: "sessions", tags: ["session", "summary"], importance: 6)
Clear ephemeral state: state_clear() for completed items
Log: memory_daily_log(type: "done", entry: "Session ended: {summary}")

Read the full file on GitHub · 104 lines

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.

4d ago First seen · 104 lines · 29 tokens per session scan A 24b4be686dc2

Subscribe to this mod's changes

session-manager is an agent published in the GitHub repository Kit4Some/Oh-my-ClaudeClaw (4 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 1,149 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.

Building agents Memory and context ai-agent ai-assistant autonomous-agent claude-code claude-code-plugin discord-bot

gemini-summarizer

Use proactively at session start (BUILDRISKMAP) and before context compaction (SUMMARIZESESSIONSTATE). Compresses session history into structured summaries preserving decisions, discarded alternatives, and unresolved debt. Writes risk maps for new repositories.

azmym/gemini-plugin · 57 tokens

session-manager