New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Self Improving For Codex

by GODGOD126 in GODGOD126/self-improving-for-codex

Build or maintain a Codex-native self-improving memory loop using global AGENTS.md, a persistent memories directory, and optional nightly refinement automation.

MITAuto-check passedAgent Workflows

Install Self Improving For Codex

skills CLI
$ npx skills add GODGOD126/self-improving-for-codex --skill self-improving-for-codex -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install GODGOD126/self-improving-for-codex self-improving-for-codex --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
self-improving-for-codex
GitHub stars
130
Token cost
~1.2k tokens
SKILL.md length
537 words
Files
7 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Build or maintain a Codex-native self-improving memory loop using global AGENTS.md, a persistent memories directory, and optional nightly refinement automation.

  • Works in 5 steps: Audit the current state → Establish the memory layout → Wire the loop through AGENTS.md → …
  • Codex needs to adapt OpenClaw-style self-improvement ideas to Codex
  • SKILL.md covers Overview, Workflow, Promotion Rules and Safety Rules, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Self Improving For Codex is an agent skill from GODGOD126/self-improving-for-codex. Build or maintain a Codex-native self-improving memory loop using global AGENTS.md, a persistent memories directory, and optional nightly refinement automation. Use when Codex needs to adapt OpenClaw-style self-improvement ideas to Codex, set up long-term user/profile memory, create PROFILE.md / ACTIVE.md / LEARNINGS.md / ERRORS.md / FEATUREREQUESTS.md, add promotion rules from raw learnings into active guidance, or create a recurring memory-refinement automation.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `README.md`, `agents/openai.yaml` and `references/agents-snippet.md`).

It sits in Agent Workflows, covering Agent instruction files and Agent memory. The repository describes itself as: A Codex-native self-improving skill based on AGENTS.md, memories, and nightly review automation. The licence is MIT.

When your agent uses it

  • Codex needs to adapt OpenClaw-style self-improvement ideas to Codex
  • Set up long-term user/profile memory
  • Create PROFILE.md / ACTIVE.md / LEARNINGS.md / ERRORS.md / FEATUREREQUESTS.md
  • Add promotion rules from raw learnings into active guidance

Example prompts

  • “/self-improving-for-codex”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Audit the current state
  2. Establish the memory layout
  3. Wire the loop through AGENTS.md
  4. Add an optional nightly review loop
  5. Validate the loop

What it can do on your machine

Read from SKILL.md and the folder at commit ae50043. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Self Improving For Codex loads about 1.2k tokens when it runs, and up to ~4.2k if it reads all its reference files. Until then it costs about 127 tokens; SKILL.md has 537 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~127
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from GODGOD126/self-improving-for-codex at commit ae50043, republished under its MIT licence (© GODGOD126). 537 words, ~1,152 tokens.

Download SKILL.mdSave it as .claude/skills/self-improving-for-codex/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
self-improving-for-codex
description
Build or maintain a Codex-native self-improving memory loop using global `AGENTS.md`, a persistent memories directory, and optional nightly refinement automation. Use when Codex needs to adapt OpenClaw-style self-improvement ideas to Codex, set up long-term user/profile memory, create `PROFILE.md` / `ACTIVE.md` / `LEARNINGS.md` / `ERRORS.md` / `FEATURE_REQUESTS.md`, add promotion rules from raw learnings into active guidance, or create a recurring memory-refinement automation.

Self-improving for Codex

Overview

Use this skill to give Codex a durable, Codex-native self-improving loop without depending on OpenClaw-only primitives such as SOUL or HEARTBEAT.md.

This skill assumes one stable rule-entry file and one stable memory directory:

  • Global rule entry: ~/.codex/AGENTS.md
  • Global memory directory: prefer ~/.codex/memories/

Workflow

1. Audit the current state

Inspect these locations first:

  • global AGENTS.md
  • the candidate memory directory
  • any existing PROFILE.md, ACTIVE.md, LEARNINGS.md, ERRORS.md, FEATURE_REQUESTS.md
  • any existing automation related to nightly review or memory maintenance

If the environment already contains a partial setup, preserve it and extend it instead of replacing it blindly.

2. Establish the memory layout

Create or normalize these files in the global memory directory:

  • PROFILE.md
  • ACTIVE.md
  • LEARNINGS.md
  • ERRORS.md
  • FEATURE_REQUESTS.md

Read references/memory-files.md when creating or repairing these files.

Use this separation consistently:

  • PROFILE.md: long-term stable user profile and communication preferences
  • ACTIVE.md: compact high-priority rules worth reading at the start of future tasks
  • LEARNINGS.md: reusable learnings and corrections not yet promoted to top-level rules
  • ERRORS.md: reusable debugging and environment failure knowledge
  • FEATURE_REQUESTS.md: missing capabilities worth tracking across sessions
3. Wire the loop through AGENTS.md

Use AGENTS.md as the single Codex-native entry point.

Its job is to tell Codex:

  • which memory files to read before starting work
  • when to log new entries
  • how to classify entries by file
  • when to promote content from raw logs into ACTIVE.md
  • that AGENTS.md itself must not be edited automatically unless the user explicitly asks

Read references/agents-snippet.md before proposing or updating the AGENTS.md text.

Unless the user explicitly asks for direct edits, propose the exact AGENTS.md snippet in chat and let the user apply it manually.

4. Add an optional nightly review loop

When the user wants recurring maintenance, create a nightly automation that:

  • reviews the current memory files
  • primarily refines LEARNINGS.md, ERRORS.md, and FEATURE_REQUESTS.md
  • proposes or applies safe updates to the memory files
  • never edits AGENTS.md automatically

Read references/nightly-review.md before designing the automation.

Show full SKILL.md (223 more words)Show less
5. Validate the loop

Before finishing, confirm the setup actually forms a loop:

  1. AGENTS.md points Codex to PROFILE.md and ACTIVE.md
  2. the five memory files exist and have sane content
  3. promotion rules are explicit
  4. if automation was requested, the automation prompt clearly explains the refinement-only role and promotion rules

Promotion Rules

Apply these promotion rules consistently:

  • Promote to ACTIVE.md only when the content is stable, cross-task useful, and likely to improve future execution or communication
  • Keep PROFILE.md limited to durable user identity, style, and preference facts
  • Keep temporary context out of PROFILE.md
  • Keep one-off noise out of all memory files
  • If a candidate item is ambiguous, keep it in a raw log or leave it as a proposal instead of promoting it

Safety Rules

  • Do not assume Codex automatically reads arbitrary memory files; route the loop through AGENTS.md
  • Do not describe OpenClaw-only mechanisms as if they exist natively in Codex
  • Do not edit AGENTS.md automatically unless the user explicitly asks
  • Prefer updating ACTIVE.md over bloating AGENTS.md
  • Prefer compact, maintainable rules over long narrative summaries

Deliverables

When using this skill, aim to produce some or all of these:

  • a memory directory with the five core files
  • a proposed AGENTS.md snippet
  • an optional nightly automation prompt
  • a short explanation of what was created, what was not changed, and how the loop works

© GODGOD126, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (references) in the repository root of GODGOD126/self-improving-for-codex.

  • SKILL.md
  • LICENSE
  • README.md
  • agents/openai.yaml
  • references/agents-snippet.md
  • references/memory-files.md
  • references/nightly-review.md

Open the folder on GitHubat commit ae50043

Compare with similar skills

Self Improving For Codex next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Self Improving For Codex compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Self Improving For Codex this skillGODGOD126/self-improving-for-codex130—~1.2kAutomated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
SkillOpt Sleep Cyclemicrosoft/SkillOpt18k—~2.3kAutomated safety check: PassMIT
CLAUDE.md Improveranthropics/claude-plugins-official38k5 repos~1.5kAutomated safety check: PassApache-2.0
Harness Engineering10xChengTu/harness-engineering1021 repos~1kAutomated safety check: PassNone
Codebase Analyzerseverity1/claude-code-auto-memory159—~1.5kAutomated safety check: PassMIT

Similar skills

  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed

  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

  • CLAUDE.md Improver

    anthropics/claude-plugins-official

    Official

    Finds every CLAUDE.md file in a repository, scores each against quality criteria, shows a report, then makes targeted updates after you approve.

    38k GitHub starsUsed in 5 repos~1.5k tokens
    Agent WorkflowsAuto-check passed

  • Harness Engineering

    10xChengTu/harness-engineering

    Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases.

    102 GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check passed

  • Codebase Analyzer

    severity1/claude-code-auto-memory

    This skill should be used when the user asks to "initialize auto-memory", "create CLAUDE.md", "set up project memory", or runs the /auto-memory:init command.

    159 GitHub stars~1.5k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed

  • CLAUDE.md Preserve

    EliaAlberti/cpr-compress-preserve-resume

    Writes this session's durable learnings into the project's CLAUDE.md and keeps the file short by archiving stale sections.

    514 GitHub stars~889 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

Categories

Questions about Self Improving For Codex

What does Self Improving For Codex do?

Build or maintain a Codex-native self-improving memory loop using global AGENTS.md, a persistent memories directory, and optional nightly refinement automation. Self Improving For Codex is an agent skill from GODGOD126/self-improving-for-codex.md, a persistent memories directory, and optional nightly refinement automation.

When should I use Self Improving For Codex?

Self Improving For Codex fits situations like: Codex needs to adapt OpenClaw-style self-improvement ideas to Codex; set up long-term user/profile memory; create PROFILE.md / ACTIVE.md / LEARNINGS.md / ERRORS.md / FEATUREREQUESTS.md; add promotion rules from raw learnings into active guidance.

How do I install Self Improving For Codex in Claude Code?

Run `npx skills add GODGOD126/self-improving-for-codex --skill self-improving-for-codex -a claude-code`. Or copy the skill folder (the GODGOD126/self-improving-for-codex repository) into .claude/skills/self-improving-for-codex in your project. Claude Code loads it when a task matches its description.

How do I install Self Improving For Codex in Codex?

Run `npx skills add GODGOD126/self-improving-for-codex --skill self-improving-for-codex -a codex`. Or copy the skill folder (the GODGOD126/self-improving-for-codex repository) into .agents/skills/self-improving-for-codex in your project. Codex loads it when a task matches its description.

Can I use Self Improving For Codex in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GODGOD126/self-improving-for-codex --skill self-improving-for-codex -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/self-improving-for-codex, .gemini/skills/self-improving-for-codex, .github/skills/self-improving-for-codex and .opencode/skills/self-improving-for-codex in your project.

What does Self Improving For Codex need to run?

SKILL.md names no scripts, command-line tools or credentials: Self Improving For Codex is instructions for the agent only.

Does Self Improving For Codex access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Self Improving For Codex safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Self Improving For Codex use?

Self Improving For Codex is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Self Improving For Codex use?

About 1.2k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3k tokens, read only when the agent opens those files.

What are the alternatives to Self Improving For Codex?

Skills that share tags, products or a category with Self Improving For Codex: Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars), SkillOpt Sleep Cycle (microsoft/SkillOpt, 18k stars), CLAUDE.md Improver (anthropics/claude-plugins-official, 38k stars) and Harness Engineering (10xChengTu/harness-engineering, 102 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Self Improving For Codex?

GODGOD126 (a GitHub user) maintains it in GODGOD126/self-improving-for-codex, which has 130 GitHub stars. The repository was last updated on August 11, 2026.

Source: GODGOD126/self-improving-for-codex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.