context-compression

context-compression is a skill for Claude Code, Codex from fabioc-aloha/Alex_Skill_Mall. It costs 47 tokens per session (3,431 once invoked), scanned A, a copy of context-compression, MIT.

Guidance for shortening long agent-session summaries while preserving decisions, changed files, risks, and next steps.

In plain words
What is it for?
Use it to design context compression, durable handoffs, and summaries for long-running coding tasks.
Why use it?
It helps an agent continue useful work after a conversation or codebase becomes too large to keep in full context.

Skill for Claude CodeCodex

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

Good fit Use it to design context compression, durable handoffs, and summaries for long-running coding tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fabioc-aloha/alex_skill_mall/context-compression
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 fabioc-aloha/Alex_Skill_Mall --skill context-compression
Clone the repo
git clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_Mall

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 context-compression

README.md
[![agentmods](https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/context-compression.svg)](https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/context-compression)
Your own site
<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/context-compression"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/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 3,431 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.
Origin 98% copy Near-identical to another mod 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 $0.03431
Opus 5 $0.00023 $0.01716
Sonnet 5 $0.00009 $0.00686
Haiku 4.5 $0.00005 $0.00343

Measured 4d ago against content hash 226c96859e68, 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 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.

Origin

This is a copy

98% identical to context-compression — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/ai-agents/context-compression/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

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. 4d ago First seen · 280 lines · 47 tokens per session scan A 226c96859e68

Subscribe to this mod's changes

context-compression is a skill published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (4 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 3,431 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to context-compression, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

catchup

Restore context after /clear by summarizing recent work and project state.

FlorianBruniaux/claude-code-ultimate-guide · 16 tokens

memory-enhancement

Manage memory citations, verify code references, and track confidence scores. Use when adding citations to memories, checking memory health, or verifying code references are still valid. Use when you say "add a citation", "verify this memory's code refs", "check memory health". Do NOT use for searching or creating…

rjmurillo/ai-agents · 80 tokens

encode-repo-serena

Populates the Forgetful knowledge base using Serena's LSP-powered symbol analysis for accurate, comprehensive codebase understanding. Use when you say "encode this repository", "populate forgetful with this codebase", "onboard to this repo", "refresh project understanding", or "build knowledge base for this project".…

rjmurillo/ai-agents · 97 tokens

exploring-knowledge-graph

Guidance for deep knowledge graph traversal across memories, entities, and relationships. Use when needing comprehensive context before planning, investigating connections between concepts, or answering "what do you know about X" questions.

rjmurillo/ai-agents · 47 tokens

memory-search

Tier 1 semantic memory search across the Serena corpus with progressive disclosure and token-budget warnings. The focused search operation split out of the memory router per ADR-063. Use when you say search memory, what do we know about X, or recall prior context. Do NOT use to extract session episodes or add…

rjmurillo/ai-agents · 77 tokens

abmind-runtime-operations

Inspect and maintain abmind memory, persona files, sleep, backups, encryption, and runtime health.

aksika/abtars · 26 tokens