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 lamenting-hawthorn/SkillLoop --skill cron-job-workflowsgit 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/cron-job-workflows)<a href="https://agentmods.dev/skills/lamenting-hawthorn/skillloop/cron-job-workflows"><img src="https://agentmods.dev/badge/skills/lamenting-hawthorn/skillloop/cron-job-workflows.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 | $0.00030 | $0.02682 |
| Opus 5 | $0.00015 | $0.01341 |
| Sonnet 5 | $0.00006 | $0.00536 |
| Haiku 4.5 | $0.00003 | $0.00268 |
Grade A, and why
cron-job-workflows 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cron Job Workflows
Use this skill whenever you are running as a scheduled cron job (your conversation starts with "[IMPORTANT: You are running as a scheduled cron job]").
Key restrictions (cron mode)
These tools/patterns are blocked in cron mode — the system cannot prompt for approval without a user present:
| Pattern | Status | Error you'll see |
|---|---|---|
execute_code() |
❌ Blocked | BLOCKED: execute_code runs arbitrary local Python... Cron jobs run without a user present to approve it. |
terminal("python3 -c '...'") |
❌ Blocked | pending_approval — matches the script execution via -e/-c flag approval pattern |
terminal("python3 << 'EOF' ... EOF") |
❌ Likely blocked | Same inline-execution approval trigger |
clarify() / asking questions |
❌ Not available | "There is no user present — you cannot ask questions, request clarification, or wait for follow-up." |
send_message() |
❌ Not needed | Your final response IS the delivery mechanism |
Proven workaround: write_file + terminal
The reliable pattern for running Python analysis in cron mode:
- Write the script with
write_file(always works — no approval needed) - Execute it with
terminal("python3 <path>")(works — shell runs a file, not inline code)
# Step 1: Write the analysis script
write_file(
path="/path/to/_tmp_report.py",
content='''#!/usr/bin/env python3
import json, os, glob, statistics
# ... your analysis logic ...
print(f"Total: {n}, Average: {avg:.2f}")
'''
)
# Step 2: Execute it
terminal("python3 /path/to/_tmp_report.py")
Cleanup
After the task, delete the temp script:
rm /path/to/_tmp_report.py
Output delivery rules
- Your final response is automatically delivered to the configured destination (email, Slack, Telegram, etc.).
- Do NOT call
send_message()or any delivery tool — let the system handle it. - If there is genuinely nothing new to report, respond with exactly
[SILENT](nothing else) to suppress delivery. - Never combine
[SILENT]with content — either report findings normally, or say[SILENT]and nothing more.
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 · 275 lines · 30 tokens per session scan A fe9136268eac
cron-job-workflows is a skill published in the GitHub repository lamenting-hawthorn/SkillLoop (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 2,682 once invoked, about $0.0002 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
model_finetuning
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.
model_finetuning
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.
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
openlore
Query and publish to an OpenLore knowledge base over SSH using ordinary shell commands. Use when a task needs project documentation, runbooks, shared team knowledge, or a place to publish findings.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.