continuous-agent-loop

continuous-agent-loop is a skill for Claude Code, Codex from jxoesneon/Ciel. It costs 20 tokens per session (544 once invoked), scanned A, original, Apache-2.0.

A set of patterns for running coding-agent work in loops with task breakdown, quality checks, evaluation, saved state, and recovery rules. An RFC-DAG is a plan where tasks and their dependencies are written down formally.

In plain words
What is it for?
Use it to choose between sequential, continuous, exploratory, or dependency-based execution and to detect when an agent is stuck repeating itself.
Why use it?
It reduces repeated failed attempts and makes long or autonomous tasks easier to control and verify.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to choose between sequential, continuous, exploratory, or dependency-based execution and to detect when an agent is stuck repeating itself.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jxoesneon/ciel/continuous-agent-loop
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 continuous-agent-loop
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 continuous-agent-loop

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jxoesneon/ciel/continuous-agent-loop"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/continuous-agent-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 544 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 $0.00020 $0.00544
Opus 5 $0.00010 $0.00272
Sonnet 5 $0.00004 $0.00109
Haiku 4.5 $0.00002 $0.00054

Measured 8d ago against content hash 825d16d949ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

continuous-agent-loop 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.

skills/continuous-agent-loop/SKILL.md · 53 lines

What it actually says

CIEL ADAPTATION: Continuous Agent Loop (Execution Stacks)

This skill formalizes the selection and management of autonomous execution loops in CIEL. It supersedes autonomous-loops by introducing a structured "Loop Selection Flow" based on task requirements.

Loop Selection Flow

  1. Sequential: Standard task-by-task execution. (Default)
  2. PR/Continuous: For tasks requiring strict CI/PR integration and branch control.
  3. RFC-DAG: For complex systems-level changes requiring formal decomposition (ralphinho-rfc-pipeline).
  4. Infinite/Exploratory: For brainstorming or parallel generation tasks without a fixed endpoint.

The Production Stack

A standard CIEL production loop consists of:

  1. Decomposition: Breaking the epic into an RFC-driven DAG.
  2. Quality Gates: Enforcing plankton-code-quality at every write boundary.
  3. Evaluation: Running eval-harness to measure behavioral correctness.
  4. Persistence: Maintaining state across session restarts via nanoclaw-repl.

Failure & Recovery

  • Churn Detection: If a loop repeats the same diagnosis 3 times without a successful verification, it is marked as "Churning."
  • Freeze & Audit: Churning loops MUST be frozen. The Orchestrator MUST run /harness-audit and reduce scope to the smallest failing unit before resuming.

Anti-Patterns

  • Unbounded Loops: Running a loop without a clear stop condition or cost cap.
  • Bypassing Gates: Disabling quality gates or tests to "speed up" the loop.
  • Silent Failures: Allowing a loop to continue after a critical tool failure without re-running the verification-loop.
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. 8d ago First seen · 53 lines · 20 tokens per session scan A 825d16d949ea

Subscribe to this mod's changes

continuous-agent-loop is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 20 tokens to every session and 544 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.

Related

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…

carbonshow/intent-fluid · 66 tokens

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…

carbonshow/intent-fluid · 101 tokens

Code Quality Review

Conduct a comprehensive code quality review focused on clean code, architecture, and project standards.

asap-protocol/asap-protocol · 21 tokens

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.

mikeshu2001/content-factory · 49 tokens

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.

mikeshu2001/content-factory · 17 tokens

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.

mikeshu2001/content-factory · 54 tokens