Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Fmarzochi/EGCnpx agentmods add skills/fmarzochi/egc/autonomous-loopsWrote 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/fmarzochi/egc/autonomous-loops)<a href="https://agentmods.dev/skills/fmarzochi/egc/autonomous-loops"><img src="https://agentmods.dev/badge/skills/fmarzochi/egc/autonomous-loops.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 | $0.00026 | $0.05443 |
| Opus 5 | $0.00013 | $0.02721 |
| Sonnet 5 | $0.00005 | $0.01089 |
| Haiku 4.5 | $0.00003 | $0.00544 |
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 4d 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.
This is a copy
86% identical to autonomous-loops — 191 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 608 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Loops Skill
Compatibility note:
autonomous-loopsis kept as a legacy alias. The canonical skill name iscontinuous-agent-loop. New loop guidance should be authored there, while this skill remains available to avoid breaking existing workflows.
Patterns, architectures, and reference implementations for running Gemini Code autonomously in loops. Covers everything from simple egc -p pipelines to full RFC-driven multi-agent DAG orchestration.
When to Use
- Setting up autonomous development workflows that run without human intervention
- Choosing the right loop architecture for your problem (simple vs complex)
- Building CI/CD-style continuous development pipelines
- Running parallel agents with merge coordination
- Implementing context persistence across loop iterations
- Adding quality gates and cleanup passes to autonomous workflows
Loop Pattern Spectrum
From simplest to most sophisticated:
| Pattern | Complexity | Best For |
|---|---|---|
| Sequential Pipeline | Low | Daily dev steps, scripted workflows |
| NanoClaw REPL | Low | Interactive persistent sessions |
| Infinite Agentic Loop | Medium | Parallel content generation, spec-driven work |
| Continuous Gemini PR Loop | Medium | Multi-day iterative projects with CI gates |
| De-Sloppify Pattern | Add-on | Quality cleanup after any Implementer step |
| Ralphinho / RFC-Driven DAG | High | Large features, multi-unit parallel work with merge queue |
1. Sequential Pipeline (egc -p)
The simplest loop. Break daily development into a sequence of non-interactive egc -p calls. Each call is a focused step with a clear prompt.
Core Insight
If you can't figure out a loop like this, it means you can't even drive the LLM to fix your code in interactive mode.
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.
- 4d ago First seen · 608 lines · 26 tokens per session scan A 1b30f0db3817
autonomous-loops is a skill published in the GitHub repository Fmarzochi/EGC (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 5,443 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to autonomous-loops, differing in 191 lines, and is treated as a copy.
Other skills, from other repositories
turborepo-caching
Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.
Flaky Test Quarantine
Detect, quarantine, and systematically fix flaky tests with automated retry analysis, root cause categorization, and CI pipeline integration for test reliability.
devops/deployment-process
A guide to releasing software through automated build, test, and deployment steps. CI/CD means automatically checking code and moving it through environments such as development, staging, and production.
Advanced Chaos Engineering
Advanced chaos engineering patterns using Chaos Monkey, Litmus, and Gremlin for testing distributed system resilience under failure conditions.
lov-npm-publisher
An npm package publishing workflow that sets up releases through GitHub Actions using OIDC, a login-free trust method, or a local granular NPM token. It covers initial setup, publishing, audit checks, and verifying the package on the npm registry.
gitlab-pipeline-debugger
Debug and monitor GitLab CI/CD pipelines for merge requests. Check pipeline status, view job logs, and troubleshoot CI failures. Use this when the user needs to investigate GitLab CI pipeline issues, check job statuses, or view specific job logs.