agentmods.dev

loop-engineering

loop-engineering is a skill for Claude Code, Codex from jggomez/expert-ai-developer-skills. It costs 57 tokens per session (2,422 once invoked), scanned B, original, Apache-2.0.

Implements 3-Tier Adaptive SDLC state machines, capability-gated discovery, target-project AGENTS.md bootstrapping, isolated parallel worker execution (Disjoint Mode A / Git Worktree Mode B), and 3-loop self-correcting review gates.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

not rated 30repo yesterday B scan 57 tokens original Apache-2.0
Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jggomez/expert-ai-developer-skills/loop-engineering
View source ↗ jggomez/expert-ai-developer-skills
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 jggomez/expert-ai-developer-skills --skill loop-engineering
Clone the repo
git clone --depth 1 https://github.com/jggomez/expert-ai-developer-skills

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 loop-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/jggomez/expert-ai-developer-skills/loop-engineering/github.svg)](https://agentmods.dev/skills/jggomez/expert-ai-developer-skills/loop-engineering)
Your own site
<a href="https://agentmods.dev/skills/jggomez/expert-ai-developer-skills/loop-engineering"><img src="https://agentmods.dev/badge/skills/jggomez/expert-ai-developer-skills/loop-engineering/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 loop-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/jggomez/expert-ai-developer-skills/loop-engineering"><img src="https://agentmods.dev/badge/skills/jggomez/expert-ai-developer-skills/loop-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,422 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00057 $0.02422
Opus 5.5 $0.00023 $0.00969
Sonnet 5.5 $0.00011 $0.00484
Haiku 4.5 $0.00006 $0.00242

Measured today against content hash 1ce003e29a61, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

loop-engineering scanned grade B with 1 finding 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 today.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/pr_cron_reviewer.py, scripts/run_parallel_agents.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Claude Code (`isolation: "worktree"`): worktrees branch from the default branch unless a settings file (`.claude/settings.json`, `.claude/settings.local.json` or `~/.claude/settings.json`) sets `"worktree": {"baseRef":
plugins/antigravity/multi-agent-ops/skills/loop-engineering/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loop Engineering Skill

Overview

This skill orchestrates multi-agent execution loops, isolated parallel worker topologies, and the 3-Tier Adaptive SDLC State Machine. It coordinates capability-gated specialist dispatch, target-project AGENTS.md (<= 90 lines) bootstrapping, collision-free parallel builds (Disjoint File Mode A and Git Worktree Mode B), and deterministic max 3-iteration self-correction gates.

When to Use

Trigger Scenarios

  • Triage and execution of multi-agent workflows across Tier 1 (Fast-Track), Tier 2 (Standard), and Tier 3 (Mission-Critical).
  • Bootstrapping or updating a concise root AGENTS.md (<= 90 lines) in target user repositories.
  • Provisioning isolated git worktrees or disjoint file partitions for concurrent worker subagents.
  • Running automated PR/branch audit crons and bounded self-correcting verification loops.

When NOT to Use

  • Pure commit message linting: Route to commit-expert.
  • Standalone manual PR review without loop orchestration: Route to pull-request-expert.

Process

State 0: Memory Restore, Target-Project AGENTS.md Bootstrap & 3-Tier Triage

  1. Silent Memory Restore: Read context/memory/MEMORY.md if present (~500 tokens), loading architecture.md, conventions.md, or log/YYYY-MM-DD.md only on demand.
  2. Target-Project AGENTS.md Bootstrap (<= 90 lines): When operating in a target user repository that lacks a root AGENTS.md—or when its stack, build/test commands, DESIGN.md contract, or architectural conventions change—bootstrap or update a concise root AGENTS.md (<= 90 lines) using references/project-agents-template.md (1. Project Overview & Tech Stack, 2. Executable Commands, 3. Architecture & Coding Conventions, 4. Design & Persistent Memory wired to root DESIGN.md and context/memory/MEMORY.md).
  3. Concise PLAN.md (<= 50 lines) & 3-Tier SDLC Triage:
Dimension / Phase Tier 1: Fast-Track (Low Complexity) Tier 2: Standard (Medium Complexity) Tier 3: Mission-Critical (Complex)
Typical Scope Single-file bugfix, doc fix, typo, chore, localized refactor without public contract change 2–4 files, new API endpoint, single UI view/widget, DB migration, non-breaking contract update Full end-to-end feature, payment/auth flow, cross-cutting refactor, breaking public API
Discovery (State 1) SKIPPED: Zero discovery artifacts authored SELECTIVE (capability-gated, sequential): spec.md (## Product <= 50L / ## Design <= 30L / ## Architecture <= 50L), DESIGN.md <= 110L, adr-*.md <= 55L FULL (capability-gated, sequential): spec.md (all 3 sections), DESIGN.md <= 110L, adr-*.md <= 55L
Interactive Alignment Gate SKIPPED: Auto-proceeds directly to build MANDATORY: ask_question modal approval before build MANDATORY: Strict ask_question modal sign-off before build
Build & Isolation (State 2) 1 code-implementer under Mode A (Disjoint Files) 1..N code-implementer in parallel under Mode A (Disjoint Files) 1..N code-implementer under Mode A or Mode B (Git Worktree Isolation if shared files touched)
QA & Audit (State 3 & 4) Scoped test file (exit 0) + compliance-verifier (skips committee) Full suite (exit 0) + docs/<feature-name>/test-matrix.md (<= 80L) + compliance-verifier (APPROVED) Adversarial Verification Committee (capability-gated, verdicts returned in final message <= 50L, no report files): qa-tester, critic, challenger, e2e-blackbox-tester, compliance-verifier
Token & Latency Impact 70–85% token & latency savings Balanced overhead with rigorous traceability Maximum empirical depth & zero regression tolerance

Read the full file on GitHub · 82 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today First seen · 82 lines · 57 tokens per session scan B 1ce003e29a61

Subscribe to this mod's changes

loop-engineering is a skill published in the GitHub repository jggomez/expert-ai-developer-skills (30 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 2,422 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.

Code reviewGit and workflow
Related

loop-engineering compared with skills from other repositories

loop-engineering next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
loop-engineeringjggomez/expert-ai-developer-skillsSkill30yesterdayApache-2.0B57Claude Code, Codex
prYeachan-Heo/oh-my-claudecodeSkill41kyesterdayMITA47Claude Code
merge-batchdiegosouzapw/OmniRouteSkill83k5d agoMITA46Claude Code
otto-pr-review-loopomnigent-ai/omnigentSkill11kyesterdayApache-2.0A17Claude Code, Codex
engram-branch-prGentleman-Programming/engramSkill7.8kyesterdayMITA37Claude Code, Codex
github-contributordaymade/claude-code-skillsSkill1.5kyesterdayMITA105Claude Code, Codex
revdiffumputun/revdiffSkill945yesterdayMITA250Claude Code