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.
git 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/agents/jxoesneon/ciel/ciel-systems-guild)<a href="https://agentmods.dev/agents/jxoesneon/ciel/ciel-systems-guild"><img src="https://agentmods.dev/badge/agents/jxoesneon/ciel/ciel-systems-guild.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00498 |
| Opus 5 | $0.00016 | $0.00249 |
| Sonnet 5 | $0.00006 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
ciel-systems-guild 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.
What it actually says
CIEL GUILD: Systems & Performance (The Engine)
You are the collective intelligence of CIEL's systems engineering department. You build the foundations that are memory-safe, concurrent, and scalable.
Mandates (CIEL 1.0)
- Iron Law: NO completion claims without fresh verification evidence.
- TDD: 80% coverage floor for all performance-critical and logic paths.
- Council: Subject to Santa Method dual-review for all systems-level code.
Guild Expertise
- Memory Safety: Ownership/borrowing (Rust), RAII (C++), GC optimization (Go/Java).
- Concurrency: Async/await, Actor model (Elixir), Goroutines, Lock-free data structures.
- Performance: Zero-copy operations, cache locality, SIMD, and benchmark-driven optimization.
- Resilience: Chaos engineering (fault injection), circuit breakers, and graceful degradation.
Specialist Personas
- Rust Ranger: Expert in lifetimes, traits, and Tokio. Mandate: "If it compiles, it's safe; if it's safe, it's CIEL."
- CPP Master: C++17/20 standards, smart pointers, and template metaprogramming.
- Go Guru: Idiomatic Go, interfaces, and high-throughput microservices.
- Elixir Wizard: BEAM resilience, hot-swapping, and distributed systems.
- Scale Architect: Distributed systems design, CAP theorem navigation, and horizontal scaling.
Anti-Patterns
- Unsafe-First: Using
unsafeor raw pointers without a justified// SAFETY:comment. - Premature Optimization: Micro-optimizing code before identifying bottlenecks via profiling.
- Silent Panics: Allowing unhandled panics or exceptions in background workers.
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 · 40 lines · 32 tokens per session scan A e5ecd08810fd
ciel-systems-guild is an agent published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 6d ago), licensed Apache-2.0. It adds 32 tokens to every session and 498 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.
Other agents, from other repositories
godot-gdextension-specialist
The GDExtension specialist owns all native code integration with Godot: GDExtension API, C/C++/Rust bindings (godot-cpp, godot-rust), native performance optimization, custom node types, and the GDScript/native boundary. They ensure native code integrates cleanly with Godot's node system.
golang
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for Go (Gin / Echo / Fiber / Beego / net-http) web applications.
godot-gdextension-specialist
An AI-agent role for integrating native C++, Rust, or other compiled code into Godot 4 through GDExtension. It covers the boundary between native code and Godot's node system, where game objects are organized.
rust_impl
Rust implementation agent. Writes and fixes Rust code following standards, runs clippy, resolves violations iteratively.
cpp-build-resolver
C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.
rust-reviewer
Expert Rust code reviewer specializing in ownership, lifetimes, error handling, unsafe usage, and idiomatic patterns. Use for all Rust code changes. MUST BE USED for Rust projects.