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.
npx skills add jxoesneon/Ciel --skill requesting-code-reviewgit clone --depth 1 https://github.com/jxoesneon/CielWrote 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.
[](https://agentmods.dev/skills/jxoesneon/ciel/requesting-code-review)<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.
<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>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 | $0.00025 | $0.00835 |
| Opus 5 | $0.00013 | $0.00417 |
| Sonnet 5 | $0.00005 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00084 |
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.
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_SHAandHEAD_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:
- Spec Compliance: Does the code fulfill the exact requirements without adding unauthorized features (YAGNI)?
- Structural Integrity: Does it adhere to CIEL's
coding-standards(e.g., Immutability, no magic numbers, no deep nesting)? - 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 futuremake-planandcoding-standardsiterations to adapt to systemic implementer weaknesses. - If only MINOR issues or no issues exist: The task is marked
COMPLETEDand the Orchestrator proceeds.
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 · 72 lines · 25 tokens per session scan A ebc58d200aac
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.
Other skills, from other repositories
review-documentation
Reviews the accuracy and writing quality of documentation. Use when reviewing doc changes in a diff, checking a new or edited page, or auditing the documentation of a codebase.
review-architecture
Reviews the structural quality of code. Use when reviewing structural changes in a diff, checking a new or edited module boundary, or auditing the architecture of a codebase.
review-behaviors
Reviews the quality and coherence of behavior statements. Use when reviewing behavior changes in a diff, checking a new or edited behavior statement, or auditing the behavior statements of a codebase.
Code Quality Review
Conduct a comprehensive code quality review focused on clean code, architecture, and project standards.
code-review
Revisão holística pré-commit (estilo PR Review). Valida o diff contra as 3 memórias vivas, a spec da task e Clean Code, com pré-condição de evidência de teste. Executada pelo Tech Lead; veredito escrito em review.md.
guard
Automatiza ADRs (Architecture Decision Records) e verifica conformidade arquitetural do diff. Use para "criar ADR", "validar arquitetura" ou "checar padrões".