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 agentmods add skills/lamenting-hawthorn/skillloop/pre-loop-checklistnpx skills add lamenting-hawthorn/SkillLoop --skill pre-loop-checklistgit clone --depth 1 https://github.com/lamenting-hawthorn/SkillLoopWrote 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/lamenting-hawthorn/skillloop/pre-loop-checklist)<a href="https://agentmods.dev/skills/lamenting-hawthorn/skillloop/pre-loop-checklist"><img src="https://agentmods.dev/badge/skills/lamenting-hawthorn/skillloop/pre-loop-checklist.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 | $0.00060 | $0.02091 |
| Opus 5 | $0.00030 | $0.01045 |
| Sonnet 5 | $0.00012 | $0.00418 |
| Haiku 4.5 | $0.00006 | $0.00209 |
Grade A, and why
pre-loop-checklist 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.
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Loop Checklist
Load this skill BEFORE creating any new cron job. It encodes the decision framework from loop engineering: should this task be a loop, or should it stay as a manual prompt?
The honest answer: most developers don't need a loop yet. This checklist saves you from building loops that cost more than they return.
When to Use
- Before calling
cronjob(action='create', ...) - When a user says "schedule this" for a coding/automation task
- Before wrapping a manual task into an unattended loop
Skip this checklist for:
- Pure watchdog scripts (
no_agent=true) — those don't use LLM tokens - One-shot scheduled messages (e.g., "remind me at 9am") — no loop involved
- Non-coding cron jobs (weather reports, news briefs, daily summaries)
Tier 1: The 4-Condition Test (Strategic)
Run this first. Miss one condition and the loop costs more than it returns.
Condition 1: The task repeats at least weekly
"If the work does not recur weekly, you don't have a loop — you have a script you ran once."
Ask: Will this task fire at least once per week?
- YES → continue to condition 2
- NO → keep it as a manual prompt or one-shot. A loop setup cost will never amortize.
Condition 2: Verification is automated
"The loop needs something that can fail the work without you in the room."
Ask: Is there a test suite, type checker, linter, or build that can reject bad output?
- YES → continue to condition 3
- NO → STOP. A loop with no real check is the agent agreeing with itself on repeat. You're back in the chair reading every diff — the exact job the loop was supposed to remove.
Condition 3: Your token budget can absorb the waste
"Loops re-read context, retry, explore. That burns tokens whether or not the run ships anything."
Ask: If this loop burns 3-5x more tokens than a single manual run (retries, re-reading context, exploration), will you still be happy?
- YES → continue to condition 4
- NO → STOP. The technique scales with budget. Solo builders on consumer plans get the token bill before the productivity gain.
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 · 232 lines · 60 tokens per session scan A 1f759c4aca2a
pre-loop-checklist is a skill published in the GitHub repository lamenting-hawthorn/SkillLoop (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 2,091 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
fine-tuning-with-trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
axolotl
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support.
mind
Local project memory with recall, provenance, policy, and dreams.
npm-security-best-practices
Apply npm/pnpm supply-chain hardening when adding a dependency, editing package.json/.npmrc/pnpm-workspace.yaml, reviewing a lockfile change, or configuring CI install steps. Covers the 17 practices from lirantal/npm-security-best-practices.
rembric-dashboard-ui
Brutalist Rembric dashboard UI work — building / editing / extending pages, styles, components, modals, tables, filters, pagination, mobile responsive, destructive confirmations. Use when the user asks for changes under src/dashboard/, mentions Rembric design tokens (lime, brutalist, sidebar, view-head, hl-lime), or…
review-and-ship
Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.