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/cxcscmu/skilllearnbench/datetime-formattingnpx skills add cxcscmu/SkillLearnBench --skill datetime-formattinggit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWhat 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 | $0.00015 | $0.01594 |
| Opus 5 | $0.00008 | $0.00797 |
| Sonnet 5 | $0.00003 | $0.00319 |
| Haiku 4.5 | $0.00002 | $0.00159 |
Grade A, and why
datetime-formatting 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 2d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Date/Time Formatting Skill
Overview
This skill covers formatting dates and times in the specific formats required for meeting confirmation replies, including proper day names, 12-hour AM/PM format, and date formatting.
Key Concepts
Required Format Specifications
Date Format: {day_name}, {month} {DD}, {YYYY}
- Example:
Thursday, January 08, 2026 - NOT:
January 8th, 2026orJanuary 8, 2026 - Two-digit day with leading zero
- Full month name (not abbreviated)
- Full day name (not abbreviated)
Time Format: {HH:MM AM/PM} - {HH:MM AM/PM}
- Example:
09:00 AM - 10:30 AM - Two-digit hour with leading zero
- Two-digit minute with leading zero (never just
9:00 AM) - Uppercase AM/PM with space before it
Code Examples
Format Date
from datetime import datetime
def format_date(date_obj):
"""Format datetime to 'Thursday, January 08, 2026' format"""
return date_obj.strftime('%A, %B %d, %Y')
# Example
d = datetime(2026, 1, 8)
print(format_date(d)) # Thursday, January 08, 2026
Format Time Range
def format_time(hour, minute, use_am_pm=True):
"""Format single time as 'HH:MM AM/PM'"""
time_obj = datetime(2026, 1, 1, hour, minute)
if use_am_pm:
return time_obj.strftime('%I:%M %p')
else:
return time_obj.strftime('%H:%M')
def format_time_range(start_hour, start_minute, end_hour, end_minute):
"""Format time range as 'HH:MM AM/PM - HH:MM AM/PM'"""
start_time = format_time(start_hour, start_minute)
end_time = format_time(end_hour, end_minute)
return f'{start_time} - {end_time}'
# Example
print(format_time_range(9, 0, 10, 30)) # 09:00 AM - 10:30 AM
print(format_time_range(13, 30, 15, 0)) # 01:30 PM - 03:00 PM
Format Duration in Hours
def format_duration(duration_hours):
"""Format duration as 'X hour(s)' - match request format"""
if duration_hours == int(duration_hours):
hours = int(duration_hours)
return f'{hours} hour' if hours == 1 else f'{hours} hours'
else:
# Handle fractional hours
total_minutes = int(duration_hours * 60)
if total_minutes % 60 == 0:
hours = total_minutes // 60
return f'{hours} hours'
else:
return f'{duration_hours} hours'
# Examples
print(format_duration(1.0)) # 1 hour
print(format_duration(1.5)) # 1.5 hours
print(format_duration(0.75)) # 0.75 hours
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.
- 2d ago First seen · 177 lines · 15 tokens per session scan A 73946ddbeeac
datetime-formatting is a skill published in the GitHub repository cxcscmu/SkillLearnBench (82 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,594 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
creating-skills
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Letta Code's capabilities with specialized knowledge, workflows, or tool integrations.
Context Doctor
Identify and repair degradation in system prompt, external memory, and skills preventing you from following instructions or remembering information as well as you should.
image-generation
Generate images from text prompts (and optionally edit/remix input images). Use when the user asks to create, generate, draw, render, or edit an image, illustration, logo, icon, diagram, or photo.
adding-models
Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update model-specific compatibility behavior. Covers runtime catalog sources, CI test matrices, and handle validation.
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
writing-bench-task-judge
Use when writing or modifying checkgoals() / getanswer() / App check methods in benchenv/task/, or when reviewing a draft task's judge correctness. Triggers include adding a new task, editing a judge method, or diagnosing a judge false-positive/negative.