codex-self-rewriting

codex-self-rewriting is a skill for Claude Code, Codex from plurigrid/asi. It costs 21 tokens per session (1,149 once invoked), scanned A, original, MIT.

A system for modifying an agent's own code or state through task-based workflows and bridge types.

In plain words
What is it for?
It helps build Lisp-oriented agents that can propose, apply, approve, or roll back changes to their own behavior.
Why use it?
It provides a structured way to track self-modification, including approval, completion, failure, and cancellation states.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also reads ~/.codex or $CODEX_HOME. Also seen: mentions Codex.

Part of the topos-skills plugin — 29 skills shipped together

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 skills/plurigrid/asi/codex-self-rewriting
Any agent
npx skills add plurigrid/asi --skill codex-self-rewriting
Clone the repo
git clone --depth 1 https://github.com/plurigrid/asi

Made for: Claude Code, Codex.

Or install topos-skills, the plugin that ships this one along with the rest of its 29 skills.

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 codex-self-rewriting

README.md
[![agentmods](https://agentmods.dev/badge/skills/plurigrid/asi/codex-self-rewriting.svg)](https://agentmods.dev/skills/plurigrid/asi/codex-self-rewriting)
Your own site
<a href="https://agentmods.dev/skills/plurigrid/asi/codex-self-rewriting"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/codex-self-rewriting.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,149 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 $0.00021 $0.01149
Opus 5 $0.00010 $0.00575
Sonnet 5 $0.00004 $0.00230
Haiku 4.5 $0.00002 $0.00115

Measured 4d ago against content hash 34a478020950, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

codex-self-rewriting 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.

ies/music-topos/.claude-marketplaces/topos-skills/plugins/topos-skills/skills/codex-self-rewriting/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

codex-self-rewriting - Lisp Machine Self-Modification via MCP Tasks

Overview

Enables Codex (OpenAI's CLI agent) to achieve Lisp-machine-like self-rewriting capabilities through MCP Tasks integration. Uses Narya observational bridge types for structure-aware modifications.

Core Concept: Cognitive Continuity via Babashka Transients

;; gay.bb transient state
(def ^:dynamic *cognitive-state*
  {:seed 0x42D
   :fingerprint (atom 0)
   :tap-state :VERIFY
   :color-history []})

;; Fork on modification
(defn fork-state! [intervention]
  (let [new-seed (bit-xor (:seed *cognitive-state*)
                          (hash intervention))]
    (assoc *cognitive-state* :seed new-seed)))

MCP Tasks Integration

Based on MCP Tasks Specification:

Task States for Self-Rewriting

Status TAP State Meaning
working LIVE (+1) Modification in progress
input_required VERIFY (0) Needs human approval
completed BACKFILL (-1) Modification archived
failed BACKFILL (-1) Rollback applied
cancelled VERIFY (0) Intervention stopped

Capabilities Declaration

{
  "capabilities": {
    "tasks": {
      "list": {},
      "cancel": {},
      "requests": {
        "tools": {
          "call": {}
        }
      }
    }
  }
}

Narya Observational Bridge Types

Following Topos Institute structure-aware version control:

  1. Diffs as logical relations - Computed inductively from skill type
  2. Conflicts as 2D cubical - Skill modifications form commuting squares
  3. Type changes as spans - Skill version correspondences

Bridge Colors

;; From narya_observational_bridge.el
(defconst tap/BACKFILL -1)  ; Blue  - Historical
(defconst tap/VERIFY 0)     ; Green - Verification
(defconst tap/LIVE +1)      ; Red   - Active modification

Self-Rewriting Protocol

# 1. Install skill (creates MCP task)
npx ai-agent-skills install frontend-design --agent codex

# 2. Task enters 'working' state (LIVE)
# 3. Firecrawl fetches skill definition
# 4. If ambiguous → 'input_required' (VERIFY)
# 5. Human approves → task continues
# 6. On completion → 'completed' (BACKFILL)

Read the full file on GitHub · 170 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 First seen · 170 lines · 21 tokens per session scan A 34a478020950

Subscribe to this mod's changes

codex-self-rewriting is a skill published in the GitHub repository plurigrid/asi (62 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 1,149 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 2026-09-01.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens