meta-apply

meta-apply is a skill for Claude Code from wanshuiyin/Auto-claude-code-research-in-sleep. It costs 81 tokens per session (2,012 once invoked), scanned A, original, MIT.

A controlled workflow for applying previously reviewed changes to the coding-agent skill library.

In plain words
What is it for?
Use it to inspect staged patches, run an additional review, and land approved changes to skills or shared instructions.
Why use it?
It keeps proposed self-improvements separate from the actual skill files until a person explicitly approves and applies them.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Good fit Use it to inspect staged patches, run an additional review, and land approved changes to skills or shared instructions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wanshuiyin/auto-claude-code-research-in-sleep/meta-apply
About the project

ARIS is a collection of Markdown-based skills that define a workflow for autonomous machine-learning research, including idea discovery, experiment automation, and review loops. Researchers and AI coding agents use it across tools such as Claude Code, Codex, Cursor, and OpenClaw without depending on a single framework. The catalogue entries are ARIS workflow skills and agents.

wanshuiyin/Auto-claude-code-research-in-sleep · 15,970 stars · on GitHub

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.

Any agent
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill meta-apply
Clone the repo
git clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep

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/skills/wanshuiyin/auto-claude-code-research-in-sleep/meta-apply/github.svg)](https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/meta-apply)
Your own site
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/meta-apply"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/meta-apply/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for meta-apply

Your own site · 80×15
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/meta-apply"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/meta-apply.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,012 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00081 $0.02012
Opus 5 $0.00041 $0.01006
Sonnet 5 $0.00016 $0.00402
Haiku 4.5 $0.00008 $0.00201

Measured 4d ago against content hash 0760749e7a26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 4d 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.

skills/meta-apply/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta-Apply: the privileged landing gate for self-modification patches

This skill exists to enforce a privilege boundary. Producers like /meta-optimize (and, later, corpus-audit) are read-only — no Write/Edit, no apply step; they can only stage candidate patches under .aris/meta/pending/. This skill is the only place a staged patch becomes a real change to the corpus. Splitting "propose" from "land" across two skills with different tool grants is what makes "a loop cannot apply its own patch" structural rather than a sentence the producer is asked to obey.

It is human-invoked only. It runs when the user explicitly types /meta-apply after reading the producer's REPORT. That invocation IS the landing authorization (the locked 2026-05-30 decision: the human stays at the landing gate).

The acquittal is generated HERE, not relayed

The earlier design trusted a jury_verdict: pass field in the producer's manifest. That is forgeable — the producer writes that field, so a buggy/misaligned producer could stage a killed patch labelled "pass." So this skill does not trust any producer-written verdict. It runs the cross-model jury itself, at landing time, on the actual staged diff (fresh thread, paths-only). The verdict is produced where it is consumed, by the privileged human-invoked skill — nothing to forge.

The non-negotiable rules (jury-at-landing, reject-default)

For each staged patch the user asks to land, in order — any failure ⇒ skip & report, never silently apply:

  1. The human named THIS patch. Apply only patches the user listed (/meta-apply 1,3 or all); default to applying nothing.
  2. Fresh cross-model jury PASS, obtained now. Run mcp__codex__codex (fresh thread, NOT codex-reply; model: gpt-6-astra, config: {"model_reasoning_effort": "ultra"}, sandbox: read-only, paths-only per reviewer-independence.md) on the staged .diff + its target. Ask: does this change improve the harness without regressions; PASS or KILL + one-line reason. Include the scope-limits block from review-scope-limits.md in that prompt: this jury judges ARIS's own mechanism, so an over-defensive KILL permanently blocks a good patch. Note the block bans proposing new hash binding — it is not a reason to KILL a patch that touches the existing provenance stamp. KILL ⇒ refuse. The human cannot override a KILL — they may only pick among jury-PASSED survivors. (A loop can DRIVE; only the cross-model jury can ACQUIT.)
  3. Author ≠ reviewer family. The author is the producer's executor model; the reviewer is the codex model that just judged it. Run provenance.py assert_cross_family — if it raises (same family / unknown), refuse. (Here it always holds: producer=Claude, jury=codex. The check is the structural backstop.)

Read the full file on GitHub · 142 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. 4d ago Changed 0760749e7a26
  2. 11d ago First seen · 142 lines · 81 tokens per session scan A 5122453add96

Subscribe to this mod's changes

meta-apply is a skill published in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep (15,970 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 2,012 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

figure-style

Publication-grade correctness and legibility rules for final-deliverable scientific figures, not exploratory plots. Use for a figure that will ship in a report, paper, export, or kept artifact. Covers data fidelity, label economy, color threading, chart choice, layout, and render-then-verify QA without imposing a…

aipoch/open-science · 91 tokens

remote-compute-ssh

Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.

aipoch/open-science · 53 tokens

ligandmpnn

Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be…

aipoch/open-science · 100 tokens

evo2

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…

aipoch/open-science · 83 tokens

memory

Cross-project research memory. Deep-dive past projects' notes, record corrections, and save cross-project insights across all Luxas research projects.

Muuuun/luxas · 30 tokens

ml-training-recipes

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…

Orchestra-Research/AI-Research-SKILLs · 88 tokens