context-engineering

A guide to managing the information given to AI agents and systems. It explains how to select useful context, handle limits, preserve memory, and coordinate multiple agents.

In plain words
What is it for?
Use it when designing agent systems, debugging lost or degraded context, reducing token use and response time, building memory, coordinating agents, or evaluating an AI pipeline.
Why use it?
Too much or poorly arranged information can make an AI system miss important details or produce weaker results. The guide helps identify and reduce these context-related failures.

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/thangchung/agent-engineering-experiment/context-engineering
Any agent
npx skills add thangchung/agent-engineering-experiment --skill context-engineering
Clone the repo
git clone --depth 1 https://github.com/thangchung/agent-engineering-experiment

Made for: Claude Code, Codex.

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 884 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 92% 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 $0.00087 $0.00884
Opus 5 $0.00044 $0.00442
Sonnet 5 $0.00017 $0.00177
Haiku 4.5 $0.00009 $0.00088

Measured 2d ago against content hash b02e54448e1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-engineering 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/compression_evaluator.py, scripts/context_analyzer.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

This is a copy

92% identical to ck:context-engineering — 36 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.

foundry-local-agent-fx/.github/skills/context-engineering/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Engineering

Context engineering curates the smallest high-signal token set for LLM tasks. The goal: maximize reasoning quality while minimizing token usage.

When to Activate

  • Designing/debugging agent systems
  • Context limits constrain performance
  • Optimizing cost/latency
  • Building multi-agent coordination
  • Implementing memory systems
  • Evaluating agent performance
  • Developing LLM-powered pipelines

Core Principles

  1. Context quality > quantity - High-signal tokens beat exhaustive content
  2. Attention is finite - U-shaped curve favors beginning/end positions
  3. Progressive disclosure - Load information just-in-time
  4. Isolation prevents degradation - Partition work across sub-agents
  5. Measure before optimizing - Know your baseline

Quick Reference

Topic When to Use Reference
Fundamentals Understanding context anatomy, attention mechanics context-fundamentals.md
Degradation Debugging failures, lost-in-middle, poisoning context-degradation.md
Optimization Compaction, masking, caching, partitioning context-optimization.md
Compression Long sessions, summarization strategies context-compression.md
Memory Cross-session persistence, knowledge graphs memory-systems.md
Multi-Agent Coordination patterns, context isolation multi-agent-patterns.md
Evaluation Testing agents, LLM-as-Judge, metrics evaluation.md
Tool Design Tool consolidation, description engineering tool-design.md
Pipelines Project development, batch processing project-development.md

Key Metrics

Read the full file on GitHub · 87 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. 2d ago First seen · 87 lines · 87 tokens per session scan A b02e54448e1f

Subscribe to this mod's changes

context-engineering is a skill published in the GitHub repository thangchung/agent-engineering-experiment (24 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 884 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to ck:context-engineering, differing in 36 lines, and is treated as a copy.

Related

Other skills, from other repositories

phoenix-cli

Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API. Use whenever the user is analyzing traces or spans, investigating LLM/agent failures, deciding…

Arize-ai/phoenix · 113 tokens

phoenix-github

Manage GitHub issues, labels, project boards, sprint operations, and roadmap health for the Arize-ai/phoenix repository. Use when filing roadmap issues, triaging bugs, applying labels, running sprint close-out and rollover, auditing board hygiene, checking ticket-load balance across the team, keeping roadmap epics up…

Arize-ai/phoenix · 90 tokens

pxi-eval-dataset

Generate synthetic evaluation datasets for the PXI eval harness (evals/pxi/). Use whenever the user asks to create, author, draft, expand, or audit an eval dataset for a PXI tool, skill, or behavior — including phrases like "write evals for ", "test PXI behavior", "synthetic dataset for PXI", "cover this tool with…

Arize-ai/phoenix · 139 tokens

phoenix-docs-gap-audit

Audit documentation gaps across the Phoenix repo by analyzing recent commits to main (default: last 7 days). Use this skill whenever the user asks to find undocumented features, identify docs gaps, audit what shipped without docs, check which recent changes need documentation, review stale docs against current code…

Arize-ai/phoenix · 155 tokens

phoenix-release-notes

Create Phoenix release documentation grounded in actual code changes. Use this skill whenever the user asks to write release notes, document a release, update release documentation, or mentions undocumented releases. Also trigger when the user wants to update GitHub release descriptions, add entries to the release…

Arize-ai/phoenix · 72 tokens

phoenix-skills-audit

Audit recent changes to Phoenix's user-facing surfaces (Python clients, TypeScript clients, CLI, REST/GraphQL APIs) and patch the three external-facing agent skills — phoenix-tracing, phoenix-cli, and phoenix-evals — so they stay in sync with what actually shipped. Use this skill whenever a user asks to update those…

Arize-ai/phoenix · 170 tokens