loop-engineering

loop-engineering is a skill for Claude Code, Codex from victor-hac-work/loop-engineering-skills. It costs 95 tokens per session (1,569 once invoked), scanned C, original, MIT.

A guided design tool for turning a rough idea into a detailed prompt and goal for an autonomous agent loop, meaning repeated runs that continue toward an objective.

In plain words
What is it for?
Use it to design self-running workflows, create a design document, review the design, and produce run instructions after approval.
Why use it?
It helps define the loop's tasks, memory, schedule, restrictions, and stored state before the loop is run.

Skill for Claude CodeCodex

Part of the loop-engineering plugin — 1 skill shipped together

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.

agentmods
npx agentmods add skills/victor-hac-work/loop-engineering-skills/loop-engineering
Any agent
npx skills add victor-hac-work/loop-engineering-skills --skill loop-engineering
Clone the repo
git clone --depth 1 https://github.com/victor-hac-work/loop-engineering-skills

Made for: Claude Code, Codex.

Or install loop-engineering, the plugin that ships this one along with the rest of its 1 skill.

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/victor-hac-work/loop-engineering-skills/loop-engineering.svg)](https://agentmods.dev/skills/victor-hac-work/loop-engineering-skills/loop-engineering)
Your own site
<a href="https://agentmods.dev/skills/victor-hac-work/loop-engineering-skills/loop-engineering"><img src="https://agentmods.dev/badge/skills/victor-hac-work/loop-engineering-skills/loop-engineering.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,569 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
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 $0.00095 $0.01569
Opus 5 $0.00048 $0.00785
Sonnet 5 $0.00019 $0.00314
Haiku 4.5 $0.00010 $0.00157

Measured 3d ago against content hash 73f8f44be306, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

loop-engineering scanned grade C 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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/init-memory.sh, scripts/scan-harness.sh), 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

prod config), forbidden commands (`git push origin main`, `rm -rf`), forbidden actions
skills/loop-engineering/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loop Engineer

Turn a rough idea into a full-context, detailed loop — a ready-to-run prompt + goal, backed by durable memory. You design the system that prompts the agent; you do not run it.

Reference (read before the dialogue): reference/loop-patterns.md.

Checklist

Create a todo per item and complete them in order:

  1. Scan harness — run scripts/scan-harness.sh.
  2. Classify the loop — deterministic vs non-deterministic.
  3. Walk the building blocks — gap-only questions, one at a time.
  4. Guardrails — ask for restrictions the loop must never cross (skippable).
  5. Scheduling — ask for a time/cadence, or skip → run as goal.
  6. Design state schema — critique the goal, derive the minimal state.
  7. Init memory — run scripts/init-memory.sh, then author goal-specific state files.
  8. Write design docdocs/loops-engineering/YYYY-MM-DD-<topic>.md.
  9. Self-review — dispatch the reference/loop-design-reviewer.md subagent.
  10. Approval gate — present design; on approval, emit the loop prompt + run instructions.

Flow

digraph loop_engineer {
  "Scan harness" -> "Classify det/non-det";
  "Classify det/non-det" -> "Non-det?";
  "Non-det?" -> "Ask goal" [label="yes"];
  "Non-det?" -> "Walk building blocks" [label="no"];
  "Ask goal" -> "Walk building blocks";
  "Walk building blocks" -> "Guardrails (skippable)";
  "Guardrails (skippable)" -> "Scheduling (or skip)";
  "Scheduling (or skip)" -> "Design state schema";
  "Design state schema" -> "Init memory + author state";
  "Init memory + author state" -> "Write design doc";
  "Write design doc" -> "Self-review subagent";
  "Self-review subagent" -> "User approves?";
  "User approves?" -> "Write design doc" [label="changes"];
  "User approves?" -> "Emit loop prompt + run instructions" [label="yes"];
}

Read the full file on GitHub · 127 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. 3d ago First seen · 127 lines · 95 tokens per session scan C 73f8f44be306

Subscribe to this mod's changes

loop-engineering is a skill published in the GitHub repository victor-hac-work/loop-engineering-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 1,569 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens