Skip to content
Agentmart
Submit a tool

context-optimize

Analyze and compress context for higher signal-to-noise ratio.

Skill by r3dlex

IndexedMIT
Write a review

Chalk Labs

Need help deploying context-optimize?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/r3dlex-context-optimize

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Analyze and compress context for higher signal-to-noise ratio. Use when GEMINI.md or session context is bloated and needs cleanup.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/context-optimize

What's inside

Skill name
context-optimize
Description
Analyze and compress context for higher signal-to-noise ratio. Use when GEMINI.md or session context is bloated and needs cleanup.
License
MIT
Instructions
62 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Context Optimize Skill (oh-my-antigravity)

## Quick Start

- Measure current context size, identify low-signal sections, then propose the smallest cleanup that improves signal density.

Optimize prompt and context files for maximum signal density.

## Quick Start
- GEMINI.md or context files have grown large and unfocused
- Session context feels bloated with stale information
- Token budget is tight and every token must count
- After a major feature addition that expanded context

## Workflow
1. **Audit**: Measure current context size and composition
2. **Score**: Rate each section for signal density (useful / total tokens)
3. **Identify issues**: Flag duplicates, stale entries, verbose sections
4. **Propose changes**: Show diff of recommended optimizations
5. **Apply**: With user approval, apply the optimizations

## Optimization Strategies

| Strategy | Description | Risk |
|----------|-------------|------|
| Deduplicate | Remove repeated instructions across layers | Low |
| Compress | Shorten verbose sections preserving meaning | Low |
| Prioritize | Move high-signal content earlier in context | Low |
| Prune | Remove stale or irrelevant entries | Medium |
| Restructure | Improve formatting for model parsing | Low |

## Metrics

```
Before: 4,200 tokens | Signal: 62% | Redundancy: 18% | Stale: 12%
After:  2,800 tokens | Signal: 89% | Redundancy: 3%  | Stale: 0%
Savings: 33% token reduction
```

## 5-Layer Context Model

oh-my-antigravity contexts follow this priority hierarchy:

1. **System/Runtime**: Gemini CLI constraints (immutable)
2. **Project Standards**: GEMINI.md + context/omg-core.md
3. **Session Memory**: .omg/state/, memory entries
4. **Active Task**: Current plan, taskboard, PRD
5. **Execution Traces**: Recent iteration results

Optimization targets layers 2-5 (layer 1 is immutable).

## Safety Rules
- Never remove user-authored content without confirmation
- Always show diff before applying changes
- Preserve semantic meaning — compress, don't delete meaning
- Back up original before modifying

## Related commands
- `/omg:optimize` — quick context optimization command
- `/omg:memory compact` — compact memory entries specifically

From r3dlex/oh-my-antigravity, MIT.

More from r3dlex/oh-my-antigravity

Signals

Stars
0
Forks
0
Open issues
2
Last commit (this folder)
May 25, 2026 (5 months ago)
Last release
May 25, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from r3dlex

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get context-optimize running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying context-optimize?

CallGet help
Cite this page

context-optimize skill. Agent Mart. https://agentmart.dev/skills/r3dlex-context-optimize (last updated 2026-10-24)