Skip to main content
skill CX Codex

meta-improve — Claude Code skill: what it does, how to install

A Claude Code skill applies operator-approved Dream candidates through a gated change process. Run it with /meta-improve-vault before building the change.

MIT ★ 26 updated 2026-11-16

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add wrg32786/aigent-os --skill meta-improve -a claude-code
Open on GitHub

What meta-improve does

meta-improve applies the smallest change that meets a candidate marked approved in vault/memory/DREAM_LOG.md. Before the build, run node daemons/nightly-contracts.mjs meta --root <aigent-root> --candidate <candidate-id> and require META_GATE PASS. The gate checks the exact status and non-placeholder evidence of operator approval.

The skill reads only the evidence references named by the candidate in LESSONS.jsonl and NIGHTLY_CAPTURE_CANDIDATES.jsonl. It runs proof before and after the change, then prepares a review artifact with the diff, commands, exit codes, residual risks, and rollback. The operator receives the accept, reject, or revise choices.

It does not approve candidates, edit Dream, push, merge, or deploy. Node.js and access to the repository root and referenced files are required for the gate.

What it helps with

  • apply an operator-approved Dream candidate
  • gate a build on candidate status and approval evidence
  • run checks before and after a proposed change
  • prepare a diff and rollback details for review

Example prompts for the agent

  • Run /meta-improve-vault for the approved Dream candidate and prepare its change for review.
  • Apply the operator-approved proposal from DREAM_LOG.md and show the diff, checks, and rollback.

How to install meta-improve

1Skills CLI (Vercel)

npx skills add wrg32786/aigent-os --skill meta-improve -a claude-code

2Manually: put the files in place

~/.claude/skills/meta-improve/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/meta-improve/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about meta-improve

How do I install meta-improve in Claude Code?

Run npx skills add wrg32786/aigent-os --skill meta-improve -a claude-code. The skill file is at ~/.claude/skills/meta-improve/SKILL.md.

What does meta-improve do?

It makes a constrained change for an operator-approved Dream candidate, runs checks, and prepares review evidence. It cannot approve candidates or merge changes.

What does meta-improve need to run?

It needs Node.js, access to the repository root, and the Dream and runtime files referenced by the candidate. The gate must return META_GATE PASS before the build.

Source text

SKILL.md · MIT
---
name: meta-improve
agent: none
description: "Run constrained self-improvement without self-approval or self-merge. Use when implementing operator-approved Dream candidates via the canonical protocol."
allowed-tools: Read, Write, Bash
user-invocable: false
status: PRODUCTION - invoke through /meta-improve-vault
---

# Constrained self-improvement

The public verb is `/meta-improve-vault`.

## Input and gate

Select only from canonical `vault/memory/DREAM_LOG.md`: an exact candidate
whose `status` is `approved` and whose approval was written by
`/dream --set-status` from a direct operator decision. `proposed` is not
approval.

Read only the exact evidence references named by that approved candidate from
`vault/memory/runtime/LESSONS.jsonl` and
`vault/memory/runtime/NIGHTLY_CAPTURE_CANDIDATES.jsonl`. Those products provide
traceability; they never provide approval by themselves.

Before Build:

```text
node daemons/nightly-contracts.mjs meta --root <aigent-root> \
  --candidate <candidate-id>
```

Require `META_GATE PASS`. It checks the canonical block for exact approved
status and non-placeholder operator evidence. This is the executable
`nightly-contracts.mjs meta` gate.

## Build

For one approved candidate:

1. Re-read its evidence, proposed change, mutation proof, and scope.
2. Use repository isolation where normal policy requires it.
3. Apply the smallest change satisfying the proposal.
4. Run the real red-before and green-after proof plus relevant system checks.
5. Produce a review artifact with exact diff, commands, exits, residual risks,
   and rollback.
6. Surface `accept / reject / revise` to the operator.

Never merge, push, deploy, broaden scope, modify an operator gate, approve
another candidate, or infer approval. A failed proof asks the Dream writer to
set the candidate `blocked`.

## Status ownership

This skill never edits Dream directly. The Dream writer owns:

- direct operator approval: `proposed -> approved`;
- verified build failure: `approved -> blocked`;
- direct rejection: `approved -> rejected`;
- independently verified merge: `approved -> merged`.

The complete flow is:

`propose -> operator gate -> build -> independent review -> operator outcome`

© wrg32786 · MIT · wrg32786/aigent-os

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set58

The whole set →
open This Claude Code skill loads workspace context and surfaces items that need attention at the start of a session. Running /open checks priorities and recovers unfinished work. CX Codex +1 ★ 26repo stars nightly This Claude Code skill runs a nightly project-state protocol and records its checkpoints. Start the full pass with /nightly-close-parity. CX Codex +1 ★ 26repo stars nightly-ledger-capture The nightly-ledger-capture Claude Code skill stages candidates for honesty, trust-decay, failure-mode, and decision-outcome records. It gathers local evidence from logs and Git; a human gate controls writes. CX Codex +1 ★ 26repo stars nightly-close-parity This skill for Claude Code runs a project’s nightly close-parity maintenance. It checks the local route first, then follows the protocol stored in the project. CX Codex +1 ★ 26repo stars memory-bridge The memory-bridge Claude Code skill connects explicit memory requests to Hindsight and Jev. Ask it to retain, recall, or reflect on a note to trigger the bridge. CX Codex +1 ★ 26repo stars Learn The Learn Claude Code skill turns research on a repo, talk, or tool into a structured note. It records an assessment and, for HOLD decisions, a condition for reviewing it again. CX Codex +1 ★ 26repo stars learn-from-failure The learn-from-failure Claude Code skill classifies failures and checks whether their causes have appeared before. Repeated problems lead to a durable artifact meant to prevent another recurrence. CX Codex +1 ★ 26repo stars impeccable The impeccable Claude Code skill guides frontend design, helps establish a project’s visual direction, and can extract components and design tokens. It needs context about users, their tasks, and the brand’s tone. CX Codex +1 ★ 26repo stars

Project sponsors

Companies that keep this analytics open