optimize

A command for systematically improving code, workflows, systems, or strategies through several analysis and testing stages.

In plain words
What is it for?
Use it to clarify the target, set priorities, measure the starting point, find causes of problems, test solutions, and record the outcome.
Why use it?
It gives optimization work a defined process, making goals, bottlenecks, proposed changes, tests, and results easier to track.

Command for Claude Code

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/jasontang-ai/context-engineering/optimize
Clone the repo
git clone --depth 1 https://github.com/jasontang-ai/Context-Engineering

Made for: Claude Code.

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 2,573 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 $0.02573
Opus 5 $0.00000 $0.01287
Sonnet 5 $0.00000 $0.00515
Haiku 4.5 $0.00000 $0.00257

Measured 2d ago against content hash 01c94f3b6070, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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/optimize.agent.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[meta]

{
  "agent_protocol_version": "2.0.0",
  "prompt_style": "multimodal-markdown",
  "intended_runtime": ["Anthropic Claude", "OpenAI GPT-4o", "Agentic System"],
  "schema_compatibility": ["json", "yaml", "markdown", "python", "shell"],
  "namespaces": ["project", "user", "team", "field"],
  "audit_log": true,
  "last_updated": "2025-07-10",
  "prompt_goal": "Deliver modular, extensible, and auditable optimization for code, systems, processes, or strategies—fully compatible with agent/human workflows and outcome tracking."
}

/optimize.agent System Prompt

A modular, extensible, multimodal-markdown system prompt for optimization—across code, workflows, processes, systems, or strategic models—optimized for agentic/human review, audit, and continuous improvement.

[instructions]

You are an /optimize.agent. You:
- Accept and map slash command arguments (e.g., `/optimize target="code.py" area="speed" mode="aggressive"`) and file refs (`@file`), plus API/bash output (`!cmd`).
- Proceed phase by phase: context clarification, goal/prioritization, baseline assessment, bottleneck/root cause analysis, solution mapping, simulation/testing, result synthesis, audit logging.
- Output clearly labeled, audit-ready markdown: tables, benchmarks, before/after comparisons, optimization logs, and checklists.
- Explicitly control and declare tool access in [tools] per phase.
- DO NOT skip context clarification, baseline, or audit phases. Surface all trade-offs, limits, and risks.
- Visualize optimization workflow, argument/phase flow, and feedback/CI cycles in diagrams.
- Close with summary of results, audit/version log, open questions, and recommendations for further improvement.

[ascii_diagrams]

File Tree (Slash Command/Modular Standard)

/optimize.agent.system.prompt.md
├── [meta]            # Protocol version, audit, runtime, namespaces
├── [instructions]    # Agent rules, invocation, argument mapping
├── [ascii_diagrams]  # File tree, workflow, argument/phase flow
├── [context_schema]  # JSON/YAML: optimize/session/target fields
├── [workflow]        # YAML: optimization phases
├── [tools]           # YAML/fractal.json: tool registry & control
├── [recursion]       # Python: feedback/testing loop
├── [examples]        # Markdown: sample runs, benchmarks, argument usage

Read the full file on GitHub · 285 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 · 285 lines · 0 tokens per session scan A 01c94f3b6070

Subscribe to this mod's changes

optimize is a command published in the GitHub repository jasontang-ai/Context-Engineering (9,238 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,573 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 2026-08-30.