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 autonomous-loopsgit 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/autonomous-loops)<a href="https://agentmods.dev/skills/jxoesneon/ciel/autonomous-loops"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/autonomous-loops/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/autonomous-loops"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/autonomous-loops.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 | $0.00031 | $0.00731 |
| Opus 5 | $0.00015 | $0.00365 |
| Sonnet 5 | $0.00006 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
autonomous-loops 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 7d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIEL ADAPTATION: Autonomous-Loops (Loop Architecture)
This skill dictates the approved architectural patterns for running autonomous agent loops within the CIEL ecosystem. It prevents chaotic, unbounded agent executions by defining structured, verifiable pipeline patterns.
Integration Context
Adapted from ~/.agents/skills/autonomous-loops/. This skill provides the high-level orchestration architectures that utilize foundational CIEL skills like subagent-driven-development, verification-loop, and safety-guard.
CIEL Approved Loop Patterns
1. The Sequential Pipeline (Standard Workflow)
The default pattern for automated tasks. Breaks work into isolated, sequential steps to prevent context degradation.
- Implement: Dispatch sub-agent for code generation.
- De-Sloppify: Dispatch a cleanup sub-agent (removes unnecessary tests, over-defensive code, console logs). Crucial: Do not use negative instructions in the Implement step; use a separate De-Sloppify pass.
- Verify: Run
verification-loop(lint, test, build). - Commit: Auto-commit with conventional messages if verified.
2. The Continuous Iteration Loop (Mid-Tier)
Used for multi-turn tasks driven by a persistent state file.
- Requires a
SHARED_TASK_NOTES.mdfile to bridge context between iterations. - Must include hard limits:
--max-runs,--max-cost, or a completion signal. - Involves an automated "Fix pass" if CI/verification fails.
3. RFC-Driven DAG Orchestration (High-Tier)
Reserved for massive, multi-file refactors or epic-level features.
- Decomposition: The Orchestrator breaks the RFC into a Dependency Graph (DAG) of discrete work units.
- Tiered Pipelines: Work units are assigned a complexity tier (trivial, small, medium, large), determining how many review/planning stages they undergo.
- Isolated Contexts: The Author sub-agent and Reviewer sub-agent MUST be different invocations with separate context windows to eliminate author-bias.
Anti-Patterns (Enforced by Orchestrator)
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.
- 7d ago First seen · 64 lines · 31 tokens per session scan A 9d52a682a4f2
autonomous-loops is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 31 tokens to every session and 731 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 2026-09-03.
Other skills, from other repositories
surge
Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…
ai-native-software-dev
Use when the user asks to build, change, modernize, or reconstruct non-trivial software with an AI-native workflow, including greenfield development, work in an existing codebase, or authorized reference-based product reconstruction; also use when lifecycle planning, architecture, implementation, testing, review…
Code Quality Review
Conduct a comprehensive code quality review focused on clean code, architecture, and project standards.
redpolicy-guide
An editorial policy for turning webinar transcripts into self-contained guides. A transcript is a written record of spoken material, while a self-contained guide can be understood without watching the webinar.
write-overview
A workflow for researching and writing a review essay about a project topic when no finished source text exists. It gathers the facts, studies example essays when available and produces the article in a project output folder.
redpolicy-article
An editorial guide for writing comparison articles about services, tools, and products. It defines a consistent entry format covering the name, link, price, description, and notable features.