context-compression

A guide to reducing the amount of conversation and project information an AI agent must process while keeping important details. It covers summaries, compaction, and checking whether key information was preserved.

In plain words
What is it for?
Use it to summarize long sessions, design context-compaction systems, reduce token use, and investigate why an agent forgets files or decisions.
Why use it?
Long agent sessions and large codebases can exceed the available context, causing slower work or forgotten decisions. The guide focuses on reducing input without creating extra work by losing information.

Skill for Claude CodeCodex

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/viktorbezdek/skillstack/context-compression
Any agent
npx skills add viktorbezdek/skillstack --skill context-compression
Clone the repo
git clone --depth 1 https://github.com/viktorbezdek/skillstack

Made for: Claude Code, Codex.

Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,907 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 $0.00131 $0.01907
Opus 5 $0.00066 $0.00954
Sonnet 5 $0.00026 $0.00381
Haiku 4.5 $0.00013 $0.00191

Measured 2d ago against content hash 07206f3582cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

context-compression/skills/context-compression/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 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 Use / Not Use

Use 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

Do NOT use when:

  • Diagnosing why context is degrading -> use context-degradation
  • KV-cache optimization or context partitioning -> use context-optimization
  • Learning foundational context theory -> use context-fundamentals
  • File-based offloading or scratch pads -> use filesystem-context

Decision Tree

Why do you need compression?
├── Agent sessions hitting context limits
│   ├── What matters most?
│   │   ├── File tracking + decision history (long sessions) -> Anchored Iterative Summarization
│   │   ├── Maximum token savings (short sessions, low re-fetch cost) -> Opaque Compression
│   │   └── Readability + phase boundaries -> Regenerative Full Summary
│   └── Not sure? -> Start with Anchored Iterative (best quality trade-off)
├── Need to measure if compression is working
│   └── Probe-based evaluation (§Probe-Based Evaluation)
├── When to trigger compression?
│   └── See §Compression Trigger Strategies
└── Not about reducing size? -> See related skills

Core Compression Approaches

Method Ratio Quality Best For
Anchored Iterative 98.6% 3.70 Long sessions where file tracking matters (coding, debugging)
Opaque 99.3% 3.35 Short sessions, maximum token savings, low re-fetch costs
Regenerative Full 98.7% 3.44 Sessions with clear phase boundaries, readability critical

Read the full file on GitHub · 176 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. 2d ago First seen · 176 lines · 131 tokens per session scan A 07206f3582cf

Subscribe to this mod's changes

context-compression is a skill published in the GitHub repository viktorbezdek/skillstack (11 stars, last pushed 2mo ago), licensed MIT. It adds 131 tokens to every session and 1,907 once invoked, about $0.0007 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

gossipcat

Use when installing or setting up gossipcat multi-agent orchestration (parallel review, consensus, adaptive dispatch) in Claude Code or Cursor. Installs the gossipcat MCP server and hands off to gossipstatus() for all live rules.

gossipcat-ai/gossipcat-ai · 50 tokens

Elephant Agent

Complete guide to what Elephant Agent is, how to use it from the CLI, how herd, wake, Personal Model, proactive curiosity, skills, and tools fit together, and how to explain Elephant Agent clearly to users, contributors, or evaluators.

agentic-in/elephant-agent · 54 tokens

libretranslate-markdown-i18n

Machine-translate Markdown / Obsidian / Quartz content into other languages using a self-hosted LibreTranslate instance, preserving frontmatter, headings, emojis, bold/italic, wikilinks (![[...]]/[[...]]) and internal links. Use whenever a user wants to auto-translate a Markdown vault, Obsidian notes, or a…

pedroiff0/awesome-skills · 127 tokens

awesome-skills-master

Master catalog orchestrator and autonomous installer for AI agents. Use when exploring, cloning, discovering, or installing skills, plugins, or MCP servers from awesome-skills without using interactive CLI tools. Guides environment detection, rule adaptation (.mdc/CLAUDE.md), MCP configuration, and strict author…

pedroiff0/awesome-skills · 66 tokens

readme-template

Standard README template for repos — professional structure with badges, overview, table of contents, features/modules, stack, installation, configuration, tests, security, structure, docs, roadmap, contribute, license, author + RepoActivity sections (Star History, repo stats) + profile GIF footer. Use when creating…

pedroiff0/awesome-skills · 72 tokens

docker-single-port-multi-instance

Consolidate multiple Docker Compose app instances (production / test / demo) behind ONE host port using an nginx reverse proxy that routes by URL path prefix (e.g. /demo). Use when a user wants 'one port, several apps/banks' or a demo reachable simultaneously from the main landing page with its own database.

pedroiff0/awesome-skills · 73 tokens