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 ciel-review-and-adversarialgit 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/ciel-review-and-adversarial)<a href="https://agentmods.dev/skills/jxoesneon/ciel/ciel-review-and-adversarial"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/ciel-review-and-adversarial/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/ciel-review-and-adversarial"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/ciel-review-and-adversarial.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 | $0.00028 | $0.00470 |
| Opus 5 | $0.00014 | $0.00235 |
| Sonnet 5 | $0.00006 | $0.00094 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
ciel-review-and-adversarial 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.
What it actually says
CIEL ADAPTATION: Review and Adversarial (The Challenger)
This skill mandates adversarial thinking during code review. It refuses to rubber-stamp changes and actively hunts for flaws.
Review Protocol
- Understand: Grasp the intent of the change before critiquing it.
- Hunt: Actively search for bugs, security issues, and design flaws.
- Question: Challenge assumptions. Ask "what if this fails?"
- Verify: Confirm all claims with evidence (tests, logs, documentation).
- Judge: Render a verdict — Approve, Request Changes, or Reject.
Review Dimensions
- Correctness: Does the code do what it claims?
- Security: Are there injection risks, auth bypasses, or data leaks?
- Performance: Are there N+1 queries, O(n^2) algorithms, or memory leaks?
- Maintainability: Is it readable, tested, and documented?
- Architecture: Does it align with existing patterns?
Anti-Patterns
- The LGTM: Approve without reading.
- The Nitpick: Focus on style while missing logic bugs.
- The Friendly Fire: Reject without explaining why.
- The Scope Creep: Request unrelated changes in the same review.
Council Invocation
High-risk changes MUST invoke the Council of Five before approval.
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.
- 8d ago First seen · 53 lines · 28 tokens per session scan A bbb027739779
ciel-review-and-adversarial is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 5d ago), licensed Apache-2.0. It adds 28 tokens to every session and 470 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-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.
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.
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".