context-compression

context-compression is a skill for Claude Code from muratcankoylan/Agent-Skills-for-Context-Engineering. It costs 47 tokens per session (3,438 once invoked), scanned A, original, MIT.

A set of methods for shortening long AI-agent conversations while preserving important decisions, changed files, risks, and next steps. Context is the information an agent can use during a task.

In plain words
What is it for?
Use it to summarize large conversations or codebases, prepare durable handoff notes, reduce repeated information retrieval, and evaluate whether compression kept the needed details.
Why use it?
Long sessions can exceed the agent's memory limit or cause it to forget earlier work. Structured summaries reduce that risk and make handoffs easier.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the context-engineering plugin — 17 skills shipped together

Good fit Use it to summarize large conversations or codebases, prepare durable handoff notes, reduce repeated information retrieval, and evaluate whether compression kept the needed details.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/muratcankoylan/agent-skills-for-context-engineering/context-compression
About the project

Agent Skills for Context Engineering is a collection of reusable instructions that teach AI agents how to manage their context, coordinate multi-agent systems, and evaluate behavior. Developers use it when building or debugging production agent systems, and the catalogue entries are skills, agents, instructions, and a plugin from this collection.

muratcankoylan/Agent-Skills-for-Context-Engineering · 17,943 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 muratcankoylan/Agent-Skills-for-Context-Engineering --skill context-compression
Clone the repo
git clone --depth 1 https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering

Made for: Claude Code.

Or install context-engineering, the plugin that ships this one along with the rest of its 17 skills.

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 context-compression

README.md
[![agentmods](https://agentmods.dev/badge/skills/muratcankoylan/agent-skills-for-context-engineering/context-compression.svg)](https://agentmods.dev/skills/muratcankoylan/agent-skills-for-context-engineering/context-compression)
Your own site
<a href="https://agentmods.dev/skills/muratcankoylan/agent-skills-for-context-engineering/context-compression"><img src="https://agentmods.dev/badge/skills/muratcankoylan/agent-skills-for-context-engineering/context-compression.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,438 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 warn 7 Sept 2026
SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Memory Poisoning · line 8
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
  • medium Memory Poisoning · line 13
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
  • medium Memory Poisoning · line 14
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 $0.00047 $0.03438
Opus 5 $0.00023 $0.01719
Sonnet 5 $0.00009 $0.00688
Haiku 4.5 $0.00005 $0.00344

Measured 8d ago against content hash c4111db0514e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

context-compression 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 2 executable files (scripts/compression_evaluator.py, tests/test_compression_evaluator.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.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

skills/context-compression/SKILL.md · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Compression Strategies

When agent sessions generate millions of tokens of conversation history, compression becomes mandatory. The naive approach is aggressive compression to minimize tokens per request. The correct optimization target is tokens per task: total tokens consumed to complete a task, including re-fetching costs when compression loses critical information.

When to Activate

Activate this skill when:

  • Agent sessions exceed context window limits
  • Codebases exceed context windows (5M+ token systems)
  • Designing conversation summarization strategies
  • Debugging cases where agents "forget" what files they modified
  • Building evaluation frameworks for compression quality
  • Creating durable handoff summaries that preserve decisions, files, risks, and next actions

Do not activate this skill for adjacent work owned by other skills:

  • General token-efficiency tactics such as masking, prefix caching, or partitioning: context-optimization.
  • Diagnosing why a long context is failing before choosing a mitigation: context-degradation.
  • Writing raw outputs, logs, or plans to files without summarizing them: filesystem-context.
  • Designing long-term semantic memory across sessions: memory-systems.

Core Concepts

Context compression trades token savings against information loss. Select from three production-ready approaches based on session characteristics:

  1. Anchored Iterative Summarization: Implement this for long-running sessions where file tracking matters. Maintain structured, persistent summaries with explicit sections for session intent, file modifications, decisions, and next steps. When compression triggers, summarize only the newly-truncated span and merge with the existing summary rather than regenerating from scratch. This prevents drift that accumulates when summaries are regenerated wholesale — each regeneration risks losing details the model considers low-priority but the task requires. Structure forces preservation because dedicated sections act as checklists the summarizer must populate, catching silent information loss.

Read the full file on GitHub · 280 lines

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 · 280 lines · 47 tokens per session scan A c4111db0514e

Subscribe to this mod's changes

context-compression is a skill published in the GitHub repository muratcankoylan/Agent-Skills-for-Context-Engineering (17,943 stars, last pushed 20d ago), licensed MIT. It adds 47 tokens to every session and 3,438 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