context

A command for reviewing and maintaining the instruction and context files that guide Claude Code in a project. It can analyze them, apply suggested cleanup, or reset them to their templates.

In plain words
What is it for?
Use it to inspect context size and import depth, optimize stale or duplicated content, consolidate files, or start again from the standard templates.
Why use it?
It helps find outdated or repeated instructions and reduce the amount of project context the agent must process. Backups are created before automatic cleanup, while reset requires confirmation.

Command

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 commands/komluk/scaffolding/context
Clone the repo
git clone --depth 1 https://github.com/komluk/scaffolding
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 436 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 $0.00019 $0.00436
Opus 5 $0.00010 $0.00218
Sonnet 5 $0.00004 $0.00087
Haiku 4.5 $0.00002 $0.00044

Measured 2d ago against content hash e2a619a960d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context 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.

commands/context.md · 92 lines

What it actually says

/context Command

Analyze and optimize Claude Code's context configuration.

Usage

/context [analyze|optimize|reset]

Modes

analyze (default)

Reviews context files and reports optimization opportunities without making changes.

Checks:

  • Token count in CLAUDE.md
  • Stale or outdated information
  • Redundant/duplicated content
  • Import chain depth
  • Knowledge-core.md size

Output:

Context Analysis Report
=======================
Total tokens: XXXX
Stale content: X sections
Redundant: X items
Potential savings: XX%

Recommendations:
1. Archive section X to knowledge-core.md
2. Remove duplicate Y
3. Consolidate imports Z

optimize

Automatically applies optimizations:

  • Archives outdated content
  • Removes duplicates
  • Consolidates sections
  • Updates imports

Safety: Creates backup before changes

reset

Restores template files and clears customizations.

Use for: Starting fresh projects

Warning: Requires confirmation

When to Run

Trigger Command
Every 50 messages /context analyze
After major refactoring /context analyze
When analysis shows 15%+ savings /context optimize
Task switching /context optimize
New project /context reset

Context Engineering Principles

Active Curation

  • Remove information not needed for current task
  • Archive completed feature docs
  • Keep only active patterns

Signal-to-Noise

  • High value: Current APIs, active patterns
  • Low value: Old experiments, completed tasks

Token Budget

  • CLAUDE.md: < 2000 tokens
  • knowledge-core.md: Archive storage
  • Imports: Max 5 hops

Performance Gains

Based on Anthropic research:

  • 39% improvement in task completion
  • 84% token reduction possible
  • Faster response times
  • More accurate outputs
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 · 92 lines · 19 tokens per session scan A e2a619a960d2

Subscribe to this mod's changes

context is a command published in the GitHub repository komluk/scaffolding (15 stars, last pushed 26d ago), licensed MIT. It adds 19 tokens to every session and 436 once invoked, about $0.0001 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.