meta-apply

meta-apply is a command for Claude Code from topprismdata/cultivating-ml-agent. It costs 19 tokens per session (580 once invoked), scanned A, original, MIT.

A command that reviews proposed updates to an agent's stored instructions or memory and applies only those approved by several other models. It is the final step after a separate analysis command suggests changes.

In plain words
What is it for?
Use it after analyzing agent logs, when updating skills from new evidence, or when refreshing outdated guidance through an approval process.
Why use it?
It reduces the risk of an agent permanently reinforcing its own mistakes or adding unverified guidance. Rejected proposals are recorded for later review.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

Good fit Use it after analyzing agent logs, when updating skills from new evidence, or when refreshing outdated guidance through an approval process.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/topprismdata/cultivating-ml-agent/meta-apply
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.

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-apply

README.md
[![agentmods](https://agentmods.dev/badge/commands/topprismdata/cultivating-ml-agent/meta-apply.svg)](https://agentmods.dev/commands/topprismdata/cultivating-ml-agent/meta-apply)
Your own site
<a href="https://agentmods.dev/commands/topprismdata/cultivating-ml-agent/meta-apply"><img src="https://agentmods.dev/badge/commands/topprismdata/cultivating-ml-agent/meta-apply.svg" alt="Measured on agentmods" height="20"></a>
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 580 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00019 $0.00580
Opus 5 $0.00010 $0.00290
Sonnet 5 $0.00004 $0.00116
Haiku 4.5 $0.00002 $0.00058

Measured 8d ago against content hash c6362d7ce2e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

meta-apply 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 8d 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-apply.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/meta-apply — Apply Memory Updates

Gated memory writes. Sends proposed changes to cross-model jury (agy/gemini/codex/ollama) for approval. Only lands changes the jury validates.

Usage

/meta-apply                    # Interactive: review each suggestion
/meta-apply --all              # Apply all after jury approval
/meta-apply <file>             # Apply to specific file

The Flow

1. /meta-optimize runs analysis
2. You review the report
3. /meta-apply proposes changes
4. Each change is sent to cross-model jury (agy)
5. Jury says: APPROVE / REJECT / REVISE
6. Only APPROVED changes land
7. Failed changes get logged to memory/meta-apply-rejected.md

Why Jury Gating

From ARIS design:

"Self-evolution layer (/meta-optimize): analyzes logs and proposes SKILL.md patches; now read-only with landing gated by cross-model jury via the new /meta-apply skill"

Without a jury:

  • Agent reinforces its own errors
  • Stale principles never get challenged
  • Conflicts slip through

When to Use

  • After /meta-optimize reports issues you agree with
  • When you want to update skills based on new evidence
  • When refreshing dead-end entries

When NOT to Use

  • During an active competition (memory changes are noise)
  • On principles you just wrote (let them age first)
  • If the changes are trivial formatting (overhead)

Jury Output Format

The jury receives:

PROPOSED CHANGE: <file>
<before>
<after>
REASON: <why this change>

And returns one of:

  • APPROVE — apply as-is
  • REJECT — don't apply, here's why
  • REVISE — here's a better version

Provenance Tracking

Every approved change is logged to memory/meta-apply-log.md:

## 2026-06-01
- File: memory/skills/500-line-rule.md
- Change: added example
- Author: meta-optimize
- Jury: agy (gemini-1.5-pro)
- Status: APPROVED

This ensures auditability: "who changed what when".

Anti-Patterns

  • --all without reading the report (rubber-stamping)
  • ❌ Ignoring REJECT verdicts (defeats purpose)
  • ❌ Skipping provenance tracking
  • ❌ Updating principles you just wrote (insufficient reflection time)

Read the full file on GitHub · 86 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. 8d ago First seen · 86 lines · 19 tokens per session scan A c6362d7ce2e5

Subscribe to this mod's changes

meta-apply is a command published in the GitHub repository topprismdata/cultivating-ml-agent (5 stars, last pushed 10d ago), licensed MIT. It adds 19 tokens to every session and 580 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.