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 ashaykubal/essential-agents-skills --skill loop-generatorgit clone --depth 1 https://github.com/ashaykubal/essential-agents-skillsWrote 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/ashaykubal/essential-agents-skills/loop-generator)<a href="https://agentmods.dev/skills/ashaykubal/essential-agents-skills/loop-generator"><img src="https://agentmods.dev/badge/skills/ashaykubal/essential-agents-skills/loop-generator/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/ashaykubal/essential-agents-skills/loop-generator"><img src="https://agentmods.dev/badge/skills/ashaykubal/essential-agents-skills/loop-generator.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 | $0.00052 | $0.03526 |
| Opus 5 | $0.00026 | $0.01763 |
| Sonnet 5 | $0.00010 | $0.00705 |
| Haiku 4.5 | $0.00005 | $0.00353 |
Grade A, and why
loop-generator 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.
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loop Generator
Turn a ratified scope into an executable loop spec. Output is a LOOP.md in the
house pattern: an outcome-shaped GOAL, an operating-model block wired to the
project's model-routing decision, GATES for owner attestations, mini-loops in
dependency order each carrying its own programmatic definition-of-done and a
ready-to-paste /goal runner condition, a default-FAIL DoD status file
whose flips are evidence-gated by hooks, guardrails whose forbidden list is
hook-implementable, and machinery (progress files, runner + fallback ladder,
verifier protocol, triggers, exit).
The pattern distills the owner's mission harnesses: loop-per-unit-of-work,
layered verification (programmatic checks decide, cross-model review on top),
enforcement via hooks rather than prose — deterministic over behavioral, on
both the write side (forbidden list) and the claim side (evidence-gated DoD
flips). A complete worked example lives in examples/ — self-contained, no
external project context required.
When to Use This Skill
| Trigger | Action |
|---|---|
| A phase scope doc is ratified and needs its implementation loop | /loop-generator docs/<scope>.md (strategy mode) |
| A house-format WP YAML needs its per-WP loop | /loop-generator plans/<slug>/workpackages/WP-X.yaml (transform mode) |
| A workpackages/ directory needs loops for every WP | /loop-generator --batch plans/<slug>/workpackages/ |
| An existing LOOP.md needs a new mini-loop added | Run in strategy mode with the LOOP.md + the new scope as inputs |
DO NOT use for: recurring/scheduled task execution (that is the built-in
/loop skill — an unrelated tool despite the name); running a loop (this skill
only authors the spec); plans that have no ratified scope yet (author the scope
or WP first — a loop generated from vibes inherits them).
Model note: strategy mode makes decomposition judgments — run it on the
planner-tier model per the owner's model policy (references/model-routing.md).
Transform mode is mechanical (the WP YAML already IS most of the filled-in
template) and runs fine on lower tiers. State which mode you are in before
starting.
What ships with it
17 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.
- examples/example-phase-loop.md 13 KB
- references/goal-runner.md 6.0 KB
- references/loop-anatomy.md 8.3 KB
- references/model-routing.md 2.9 KB
- references/outer-runner.md 11 KB
- references/review-termination-product-clean.md 6.4 KB
- references/rigor-calibration.md 4.9 KB
- references/sandbox-provisioning.md 10.0 KB
- templates/hooks/commit-backstop.sh 1.3 KB runs code
- templates/hooks/forbidden-paths.sh 4.9 KB runs code
- templates/hooks/gate-dod-status.sh 1.2 KB runs code
- templates/hooks/README.md 3.2 KB
- templates/hooks/settings-snippet.json 587 B
- templates/hooks/track-evidence.sh 723 B runs code
- templates/LOOP-template.md 7.2 KB
- templates/runner-template.sh 8.8 KB runs code
- templates/SUPERVISOR-template.md 6.2 KB
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.
- 8d ago First seen · 257 lines · 52 tokens per session scan A e52767a46eba
loop-generator is a skill published in the GitHub repository ashaykubal/essential-agents-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 3,526 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…