requesting-code-review

requesting-code-review is a skill for Claude Code, Codex from jxoesneon/Ciel. It costs 25 tokens per session (835 once invoked), scanned A, original, Apache-2.0.

A formal process for having a separate auditor review code changes against the requirements and coding standards.

In plain words
What is it for?
It is for preparing isolated review context, sharing the relevant Git diff and requirements, and checking whether an implementation meets its specification.
Why use it?
Separating the writer from the reviewer reduces author bias and makes the review focus on the delivered changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit It is for preparing isolated review context, sharing the relevant Git diff and requirements, and checking whether an implementation meets its specification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jxoesneon/ciel/requesting-code-review
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 jxoesneon/Ciel --skill requesting-code-review
Clone the repo
git clone --depth 1 https://github.com/jxoesneon/Ciel

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 requesting-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/jxoesneon/ciel/requesting-code-review/github.svg)](https://agentmods.dev/skills/jxoesneon/ciel/requesting-code-review)
Your own site
<a href="https://agentmods.dev/skills/jxoesneon/ciel/requesting-code-review"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/requesting-code-review/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 requesting-code-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/jxoesneon/ciel/requesting-code-review"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/requesting-code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 835 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 $0.00025 $0.00835
Opus 5 $0.00013 $0.00417
Sonnet 5 $0.00005 $0.00167
Haiku 4.5 $0.00003 $0.00084

Measured 6d ago against content hash ebc58d200aac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

requesting-code-review 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.

skills/requesting-code-review/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CIEL ADAPTATION: Requesting Code Review (The Auditor Protocol)

This skill formalizes the "Code Quality Review" stage of CIEL's subagent-driven-development cycle. It dictates how the Orchestrator requests a peer review from the Auditor sub-agent, ensuring that reviews are objective, context-isolated, and strictly aligned with CIEL standards.

Integration Context

Adapted from ~/.agents/skills/requesting-code-review/. This skill is the mechanism by which the Orchestrator enforces the coding-standards skill. It guarantees that the agent writing the code is never the same agent reviewing the code (eliminating author-bias).

The Code Review Protocol

1. Context Isolation (Mandatory)

When dispatching the Auditor sub-agent, the Orchestrator MUST NOT pass its own entire session history. The reviewer must judge the work product, not the thought process.

Required Context for the Auditor:

  • BASE_SHA and HEAD_SHA (or the specific git diff).
  • The original Task Specification / Requirements.
  • A brief summary of what was implemented.

2. Evaluation Rubric

The Auditor sub-agent must evaluate the diff against the following rubric:

  1. Spec Compliance: Does the code fulfill the exact requirements without adding unauthorized features (YAGNI)?
  2. Structural Integrity: Does it adhere to CIEL's coding-standards (e.g., Immutability, no magic numbers, no deep nesting)?
  3. Test Coverage: Are there meaningful tests included for the new business logic?

3. Feedback Categorization

The Auditor must categorize issues into three levels:

  • CRITICAL: Security flaws, infinite loops, broken builds. Must be fixed immediately.
  • IMPORTANT: Violations of coding-standards, missing tests, logic errors. Must be fixed before the task is marked COMPLETED.
  • MINOR: Nitpicks, styling, optional refactors. Can be noted for later or ignored.

4. Orchestrator Action

Upon receiving the Auditor's report:

  • If CRITICAL or IMPORTANT issues exist: The Orchestrator MUST dispatch a fix sub-agent (or the original implementer) with the review feedback to resolve the issues. Proceeding without fixing these is a violation of the protocol.
  • Evolutionary Feedback (Meta-Learning): The Orchestrator MUST log recurring structural or logic failures to the MemPalace Knowledge Graph (mempalace_kg_add). This allows future make-plan and coding-standards iterations to adapt to systemic implementer weaknesses.
  • If only MINOR issues or no issues exist: The task is marked COMPLETED and the Orchestrator proceeds.

Read the full file on GitHub · 72 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. 6d ago First seen · 72 lines · 25 tokens per session scan A ebc58d200aac

Subscribe to this mod's changes

requesting-code-review is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 25 tokens to every session and 835 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 2026-09-03.