memory-summarization

memory-summarization is a skill for Claude Code from a5c-ai/babysitter. It costs 14 tokens per session (342 once invoked), scanned A, original, MIT.

A set of methods for shortening conversation history into summaries. It supports rolling, hierarchical, extractive, and model-generated summaries while considering the available token limit.

In plain words
What is it for?
Use it to maintain conversational memory, update rolling summaries, select key messages, fit context budgets, and evaluate summary quality.
Why use it?
Long conversations can exceed the amount of text a language model can process at once. Summarizing preserves important context while reducing the space needed for older messages.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

About the project

Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.

a5c-ai/babysitter · 1,769 stars · on GitHub · a5c.ai

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 skills/a5c-ai/babysitter/memory-summarization
Any agent
npx skills add a5c-ai/babysitter --skill memory-summarization
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

Made for: Claude Code.

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.

agentmods badge for memory-summarization

README.md
[![agentmods](https://agentmods.dev/badge/skills/a5c-ai/babysitter/memory-summarization.svg)](https://agentmods.dev/skills/a5c-ai/babysitter/memory-summarization)
Your own site
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/memory-summarization"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/memory-summarization.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 342 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.00342
Opus 5 $0.00007 $0.00171
Sonnet 5 $0.00003 $0.00068
Haiku 4.5 $0.00001 $0.00034

Measured today against content hash 70a42c074cf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

memory-summarization 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 today.

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.

library/specializations/ai-agents-conversational/skills/memory-summarization/SKILL.md · 66 lines

What it actually says

Memory Summarization Skill

Capabilities

  • Implement conversation summarization strategies
  • Configure rolling summary updates
  • Design hierarchical summarization
  • Implement token-aware summarization
  • Create extractive and abstractive summaries
  • Design summary quality evaluation

Target Processes

  • conversational-memory-system
  • long-term-memory-management

Implementation Details

Summarization Strategies

  1. Rolling Summary: Update summary with new messages
  2. Hierarchical: Multi-level summarization
  3. Token-Budget: Fit within token limits
  4. Extractive: Key message selection
  5. Abstractive: LLM-generated summaries

Configuration Options

  • LLM for summarization
  • Summary token budget
  • Update frequency
  • Summary template
  • Quality thresholds

Best Practices

  • Balance detail vs compression
  • Preserve key information
  • Monitor summary quality
  • Test with long conversations
  • Handle context window limits

Dependencies

  • langchain-core
  • LLM provider
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. today First seen · 66 lines · 14 tokens per session scan A 70a42c074cf6

Subscribe to this mod's changes

memory-summarization is a skill published in the GitHub repository a5c-ai/babysitter (1,769 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 342 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 2026-09-05.

Related

Other skills, from other repositories

reflect

Mines a session for durable learnings. Trigger on "reflect on this session", "capture what we learned", or "/reflect" only; never infer intent from session end or friction.

bostonaholic/team · 40 tokens

list-learned-actions

Explicit Codex workflow: List persisted reusable actions, UI skeletons, and legacy feedback memories before composing device primitives.

Lykhoyda/rn-dev-agent · 29 tokens

agent-memory-coordinator

Agent skill for memory-coordinator - invoke with $agent-memory-coordinator.

ruvnet/ruflo · 19 tokens

tutti-agent-workspace-app

Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…

tutti-os/tutti · 106 tokens

external-memory-plugin

Develop, adapt, review, test, and troubleshoot Nexent external memory provider plugins, including plugin.yaml manifests, searchable and ingestible provider protocols, error mapping, network-isolated unit tests, deployment configuration, and Mem0-based examples. Use when adding a new external memory vendor, changing an…

ModelEngine-Group/nexent · 85 tokens

distill-session-knowledge

Offline-mine this project's pi session JSONL logs into reusable, verified knowledge: extracts faults, decisions, corrections, procedures and docs, promotes only recurring patterns, and routes artifacts into skillmanage, memory and docs. Use on "mine my sessions", "distill session knowledge", "extract lessons from…

BlackBeltTechnology/pi-agent-dashboard · 78 tokens