codex-claude-mcp: Skill for Claude Code

.agents/skills/executing-noodle-plans/SKILL.md

executing-noodle-plans is a skill for Claude Code, Codex from Cyruskraad/codex-claude-mcp. It costs 44 tokens per session (742 once invoked), scanned A, original, MIT.

A process for carrying out an already approved implementation plan in a Noodle Seed project. It uses test-first development, or TDD, where a failing test is written before the code that should pass it.

In plain words
What is it for?
Use it to implement planned changes one task at a time, review the work, recover from failures, and run the required final checks.
Why use it?
It keeps work aligned with settled decisions, limits changes to the plan, and checks each task before moving on.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Cyruskraad/codex-claude-mcp's own configuration. It tells Claude Code and Codex how to work on codex-claude-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codex-claude-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Cyruskraad/codex-claude-mcp. 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/Cyruskraad/codex-claude-mcp/main/.agents/skills/executing-noodle-plans/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Cyruskraad/codex-claude-mcp

Made for: Claude Code, Codex.

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 executing-noodle-plans

README.md
[![agentmods](https://agentmods.dev/badge/skills/cyruskraad/codex-claude-mcp/executing-noodle-plans/github.svg)](https://agentmods.dev/skills/cyruskraad/codex-claude-mcp/executing-noodle-plans)
Your own site
<a href="https://agentmods.dev/skills/cyruskraad/codex-claude-mcp/executing-noodle-plans"><img src="https://agentmods.dev/badge/skills/cyruskraad/codex-claude-mcp/executing-noodle-plans/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 executing-noodle-plans

Your own site · 80×15
<a href="https://agentmods.dev/skills/cyruskraad/codex-claude-mcp/executing-noodle-plans"><img src="https://agentmods.dev/badge/skills/cyruskraad/codex-claude-mcp/executing-noodle-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 742 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.
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 $0.00044 $0.00742
Opus 5 $0.00022 $0.00371
Sonnet 5 $0.00009 $0.00148
Haiku 4.5 $0.00004 $0.00074

Measured 8d ago against content hash 81845b2adcd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

executing-noodle-plans 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 8d 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.

.agents/skills/executing-noodle-plans/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute a Noodle Seed implementation plan

Execute an approved plan without reopening settled design decisions. Keep implementation, review, and evidence scoped to the current repository and the authority the user granted.

Preconditions

  • Read the plan, repository instructions, current branch status, and the files named by the first incomplete task.
  • Confirm the plan is decision-complete, test-first, compatible with the current code, and explicit about public contracts and required verification.
  • Work in the repository-required isolated branch or worktree and preserve unrelated changes.
  • If current code invalidates the plan or two requirements conflict, stop before editing and ask which requirement governs.

Task loop

Execute one task at a time in plan order:

  1. Restate the task boundary, expected behavior, focused failing test, and files in scope.
  2. Add or update the focused test first and run it to confirm the expected failure when practical.
  3. Implement only the behavior required to make that test pass. Do not add compatibility paths, abstractions, or adjacent cleanup the plan did not require.
  4. Run the focused test, then the package-level checks named by the plan.
  5. Review the task diff for plan compliance, correctness, security, type safety, and unnecessary surface area.
  6. Record completion in the plan checkbox when it is writable and in a focused conventional commit.

When the active host provides isolated task workers and user authorization permits delegation, use a fresh implementer for an independent task and a separate reviewer after it. Give each worker only the task requirements, binding global constraints, file paths, and required evidence. Never run workers in parallel when their files or contracts overlap. Execute inline when workers are unavailable, tasks are tightly coupled, or delegation is not authorized.

Review and recovery

  • Independent review must compare the task requirements with the exact task diff and test evidence; implementer self-review does not replace it when a reviewer is available.
  • Return concrete findings to the implementer, rerun the tests that cover each correction, and review the correction diff again.
  • Allow at most three correction rounds for the same finding. Then stop with the unresolved requirement, attempted fixes, and current evidence instead of silently accepting drift.
  • On context loss or interruption, resume from the plan checkboxes, git status, and git log; verify the last completed task before starting the first incomplete one.

Read the full file on GitHub · 52 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. 8d ago First seen · 52 lines · 44 tokens per session scan A 81845b2adcd1

Subscribe to this mod's changes

executing-noodle-plans is a skill published in the GitHub repository Cyruskraad/codex-claude-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 44 tokens to every session and 742 once invoked, about $0.0002 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.