What is clodex CLAUDE.md?

A project-instructions file for clodex, a Claude Code plugin that runs a plan, implementation, review, and fix cycle on a feature branch. It explains the project’s architecture and which component is responsible for each part of the cycle.

Guiding work on clodex code, explaining its four-layer design, and specifying how planning, focused execution, review, and finding fixes fit together.

It gives agents the project’s source of truth before they change code, reducing mistakes caused by misunderstanding the roles of clodex and Codex.

How lukaskucinski/clodex configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lukaskucinski/clodex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lukaskucinski/clodex/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lukaskucinski/clodex

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lukaskucinski/clodex/claude-md.svg)](https://agentmods.dev/instructions/lukaskucinski/clodex/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lukaskucinski/clodex/claude-md"><img src="https://agentmods.dev/badge/instructions/lukaskucinski/clodex/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,108 This file is loaded in full into every session.

When invoked 2,108 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02108	$0.02108
Opus 5	$0.01054	$0.01054
Sonnet 5	$0.00422	$0.00422
Haiku 4.5	$0.00211	$0.00211

Measured 6d ago against content hash 92fb0c980405, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

clodex CLAUDE.md 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 6d 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.

CLAUDE.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — clodex project guidance

Read this before touching any clodex code. Concise; if you need depth see skills/clodex/HARD_RULES.md (authoritative) and README.md (full history).

What clodex is

A Claude Code plugin that drives an autonomous plan → ship → review → fix loop on a feature branch. The "review" is performed by OpenAI's codex CLI (via the codex Claude-Code plugin's codex-companion.mjs script), NOT by another Claude instance. Clodex orchestrates; codex reviews; clodex fixes; repeat until codex approves, only sub-threshold findings remain, or the iteration cap is hit.

Architecture: the four-layer stack

Layer 1 (orchestration)   /clodex slash command  → skills/clodex/SKILL.md (the loop controller)
Layer 2 (subagents)       clodex-focus-runner    → agents/clodex-focus-runner.md  (Phase 4a)
                          clodex-findings-fixer  → agents/clodex-findings-fixer.md (Phase 4f)
Layer 3 (review plumbing) node codex-companion.mjs adversarial-review (codex plugin)
Layer 4 (model call)      codex.exe app-server   → OpenAI API (codex CLI binary)

Clodex owns Layers 1 + 2. Layer 3 is the codex plugin (don't reimplement; just invoke it correctly). Layer 4 is the codex CLI binary on disk; clodex never touches it.

The four hard rules (mirror of HARD_RULES.md — that file wins on conflict)

Codex is the only review pass. Underlying call MUST be node "$COMPANION_SCRIPT" <subcommand> via Bash. PowerShell is forbidden for codex-companion subcommands.
Plugin-state operations (positive contract — Bash-mandatory). Allowed: read plugin state, invoke companion script via Bash, kill broker PID via PowerShell Stop-Process (the ONLY PowerShell carve-out, max 2 per run), write to .clodex/ and implementation files. Everything else forbidden.
Always dispatch clodex-focus-runner for Phase 4a. Never write focus text inline.
Halt and surface, do not improvise. If a prescribed step fails unexpectedly, halt — do not invent workarounds.

Read the full file on GitHub · 89 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.

6d ago First seen · 89 lines · 2,108 tokens per session scan A 92fb0c980405

Subscribe to this mod's changes

clodex CLAUDE.md is an instructions file published in the GitHub repository lukaskucinski/clodex (2 stars, last pushed 3mo ago), licensed MIT. It adds 2,108 tokens to every session, about $0.0105 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.

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

clodex: Instructions file for Claude Code