context-optimize

A command for tracking and reducing the amount of conversation context an AI coding agent is using. It can check usage, save phase checkpoints, load named resources from an Obsidian vault, and compress context.

In plain words
What is it for?
Use it to inspect context usage, save research or implementation checkpoints, restore agent, skill, tool, or workflow definitions, and create a budget report.
Why use it?
Long agent sessions can run out of room or lose important information. This command keeps phase summaries and removes less-important context so work can continue.

Command for Claude Code

Part of the claude-orchestration plugin — 49 commands, 9 agents shipped together

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/thelobbi/claude/context-optimize
Clone the repo
git clone --depth 1 https://github.com/TheLobbi/claude

Made for: Claude Code.

Or install claude-orchestration, the plugin that ships this one along with the rest of its 49 commands, 9 agents.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 610 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 $0.00000 $0.00610
Opus 5 $0.00000 $0.00305
Sonnet 5 $0.00000 $0.00122
Haiku 4.5 $0.00000 $0.00061

Measured 2d ago against content hash ab6095972d20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-optimize 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.

.claude/commands/context-optimize.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Optimization Command

Usage: /context-optimize [action]

Manages context optimization through external knowledge base and checkpointing.

Actions

status - Check Current Context Usage

/context-optimize status

Shows:

  • Current token usage across all components
  • Budget health status
  • Active allocations
  • Optimization suggestions

checkpoint - Create Phase Checkpoint

/context-optimize checkpoint [phase]

Creates external checkpoint for phase:

  • explore - Research findings
  • plan - Implementation plan
  • code - Code implementation
  • test - Test results
  • fix - Bug fixes
  • document - Documentation

load - Load External Resource

/context-optimize load [type] [name]

Load resource from Obsidian vault:

  • agent [name] - Load agent definition
  • skill [name] - Load skill definition
  • mcp [name] - Load MCP tool reference
  • workflow [name] - Load workflow pattern

compress - Compress Current Context

/context-optimize compress

Triggers automatic context compression:

  1. Checkpoints active phase
  2. Releases non-essential allocations
  3. Keeps only 200-token summaries

report - Generate Budget Report

/context-optimize report

Generates comprehensive budget report with:

  • Token usage breakdown
  • Allocation efficiency
  • Optimization recommendations
  • Historical trends

Examples

# Check context health
/context-optimize status

# Checkpoint CODE phase
/context-optimize checkpoint code

# Load coder agent definition
/context-optimize load agent coder

# Compress context when approaching limits
/context-optimize compress

# Get detailed budget report
/context-optimize report

Integration with Orchestration

This command works seamlessly with the 6-phase orchestration protocol:

EXPLORE → checkpoint → 200 tokens
PLAN → checkpoint → 150 tokens
CODE → checkpoint → 300 tokens
TEST → checkpoint → 200 tokens
FIX → checkpoint → 150 tokens
DOCUMENT → checkpoint → 200 tokens

Read the full file on GitHub · 125 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 · 125 lines · 0 tokens per session scan A ab6095972d20

Subscribe to this mod's changes

context-optimize is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 610 tokens. 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 2026-08-31.