strands-context-manager

strands-context-manager is a skill for Claude Code, Codex from aws-samples/sample-agent-skills-for-builders. It costs 37 tokens per session (436 once invoked), scanned A, original, Apache-2.0.

A conversation manager for Strands agents, the software framework used to build AI agents. It keeps recent messages in view and summarizes older parts when conversations become long.

In plain words
What is it for?
Use it when building Strands agents that need to manage long conversations, compact old messages, or avoid session pollution in multi-turn interactions.
Why use it?
It prevents the conversation history from growing beyond the model’s context limit or carrying irrelevant details into later turns. The guidance also addresses recursion and setup problems during summarization.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one.

Good fit Use it when building Strands agents that need to manage long conversations, compact old messages, or avoid session pollution in multi-turn interactions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aws-samples/sample-agent-skills-for-builders/strands-context-manager
About the project

Sample Agent Skills for Builders is a collection of reusable skills that extend AI coding agents with AWS, CDK, security, testing, and engineering workflows. Developers can install the skills for practical AWS development tasks or use the repository as a model for creating their own agent skills. The catalogue entries are skills and instructions from this collection.

aws-samples/sample-agent-skills-for-builders · 47 stars · on GitHub

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.

Any agent
npx skills add aws-samples/sample-agent-skills-for-builders --skill strands-context-manager
Clone the repo
git clone --depth 1 https://github.com/aws-samples/sample-agent-skills-for-builders

Made for: Claude Code, Codex.

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 strands-context-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/aws-samples/sample-agent-skills-for-builders/strands-context-manager.svg)](https://agentmods.dev/skills/aws-samples/sample-agent-skills-for-builders/strands-context-manager)
Your own site
<a href="https://agentmods.dev/skills/aws-samples/sample-agent-skills-for-builders/strands-context-manager"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-agent-skills-for-builders/strands-context-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 436 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00037 $0.00436
Opus 5 $0.00018 $0.00218
Sonnet 5 $0.00007 $0.00087
Haiku 4.5 $0.00004 $0.00044

Measured 8d ago against content hash 8f93e44d3e50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

strands-context-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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/strands-context-manager.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/strands-context-manager/SKILL.md · 70 lines

What it actually says

Strands Context Manager (Sliding Window with Summarization)

Strands Agents SDK conversation manager combining sliding window and summarization strategies.

When to Apply

Reference this skill when:

  • Building Strands agents with long conversations
  • Implementing context window management
  • Preventing session pollution in multi-turn dialogs
  • Combining sliding window with summarization

Critical Pitfalls

1. Inheritance Pitfall

DON'T inherit from SummarizingConversationManager. DO inherit from base ConversationManager.

2. Infinite Recursion

Use _is_summarizing flag with try/finally to prevent recursion during summarization calls.

3. Hook Closure Problem (MOST CRITICAL)

Lambda closures capture session_manager references during initialization. Create summarization agent WITHOUT session_manager, hooks, or persistence.

Implementation Pattern

class SlidingWindowWithSummarizationManager(ConversationManager):
    def __init__(self, window_size=40, summarization_agent=None, summarization_system_prompt=None):
        self._is_summarizing = False
        self._summarization_agent = summarization_agent  # Lazy init when None

    def _get_summarization_agent(self):
        # Create clean agent without session_manager
        return Agent(
            # NO session_manager, NO hooks
        )

Usage

from conversation_manager import SlidingWindowWithSummarizationManager

manager = SlidingWindowWithSummarizationManager(
    window_size=20,
)

Critical Test

def test_no_session_pollution():
    # Verify internal messages don't persist
    # Verify no "Please summarize" in session

References

Files

What ships with it

3 files 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. 8d ago First seen · 70 lines · 37 tokens per session scan A 8f93e44d3e50

Subscribe to this mod's changes

strands-context-manager is a skill published in the GitHub repository aws-samples/sample-agent-skills-for-builders (47 stars, last pushed 12d ago), licensed Apache-2.0. It adds 37 tokens to every session and 436 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens