meta-optimize

meta-optimize is a command for Claude Code from topprismdata/cultivating-ml-agent. It costs 16 tokens per session (389 once invoked), scanned A, original, MIT.

A read-only command that examines the memory/ folder for outdated files, contradictions, missing index entries, oversized documents, coverage gaps, and broken links.

In plain words
What is it for?
Use it to run a memory health check and review issues before deciding whether entries should be refreshed, archived, or removed.
Why use it?
It shows where stored project knowledge may be stale, incomplete, inconsistent, or difficult to navigate without changing anything.

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/topprismdata/cultivating-ml-agent/meta-optimize
Clone the repo
git clone --depth 1 https://github.com/topprismdata/cultivating-ml-agent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for meta-optimize

README.md
[![agentmods](https://agentmods.dev/badge/commands/topprismdata/cultivating-ml-agent/meta-optimize.svg)](https://agentmods.dev/commands/topprismdata/cultivating-ml-agent/meta-optimize)
Your own site
<a href="https://agentmods.dev/commands/topprismdata/cultivating-ml-agent/meta-optimize"><img src="https://agentmods.dev/badge/commands/topprismdata/cultivating-ml-agent/meta-optimize.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 389 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 5.1 $0.00016 $0.00389
Opus 5 $0.00008 $0.00195
Sonnet 5 $0.00003 $0.00078
Haiku 4.5 $0.00002 $0.00039

Measured 5d ago against content hash b6759e9df26b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

meta-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 5d 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.

ml-agent-code-template/.claude/commands/meta-optimize.md · 59 lines

What it actually says

/meta-optimize — Memory Health Check

Read-only analysis of memory/. Reports issues. Does not modify anything.

Usage

/meta-optimize
/meta-optimize --json

What This Does

Runs bash .claude/hooks/meta_optimize.sh which scans memory/ and reports:

  1. Staleness — files not modified in 90+ days
  2. Oversized files — > 500 lines (violates 500-line rule)
  3. Missing index entries — files not in MEMORY.md
  4. Possible contradictions — principles with conflicting language
  5. Coverage gaps — breakthrough experiments without extracted skills
  6. Stale dead-ends — feedback entries > 365 days old
  7. Broken internal links — markdown links to non-existent files

Output

Human-readable report. For machine-readable output, use --json.

Workflow After Running

1. /meta-optimize           # see issues
2. For each issue, decide: refresh / archive / remove
3. /meta-apply <changes>    # cross-model jury required for landing

Why Read-Only

This skill never modifies memory directly. From ARIS design:

"self-evolution is read-only with landing gated by cross-model jury"

Agents modifying their own memory can reinforce errors. External review catches this.

When to Use

  • Weekly during long projects
  • Before major phase changes
  • After a competition completes
  • When you suspect memory is becoming stale

When NOT to Use

  • Daily (overhead)
  • On tiny memory (< 10 files)
  • When actively debugging a problem (not the time)
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. 5d ago First seen · 59 lines · 16 tokens per session scan A b6759e9df26b

Subscribe to this mod's changes

meta-optimize is a command published in the GitHub repository topprismdata/cultivating-ml-agent (4 stars, last pushed 8d ago), licensed MIT. It adds 16 tokens to every session and 389 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 2026-08-31.