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/github-metrics-processingnpx skills add cxcscmu/SkillLearnBench --skill github-metrics-processinggit 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 | $0.00029 | $0.01276 |
| Opus 5 | $0.00015 | $0.00638 |
| Sonnet 5 | $0.00006 | $0.00255 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
github-metrics-processing 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.
GitHub Metrics Processing Skill
Overview
Process JSON data from GitHub queries to calculate publication metrics, including PR merge times, issue categorization, and contributor analysis.
Prerequisites
- Python 3.7+ with
jsonanddatetimemodules (standard library) - Raw GitHub API JSON data from gh CLI queries
Key Metrics to Calculate
Pull Request Metrics
1. Total PR Count
total_prs = len(prs_data)
2. Merged vs Closed PRs
merged_prs = [pr for pr in prs_data if pr.get('mergedAt') is not None]
closed_prs = [pr for pr in prs_data if pr.get('closedAt') is not None and pr.get('mergedAt') is None]
merged_count = len(merged_prs)
closed_count = len(closed_prs)
3. Average Merge Time (days)
from datetime import datetime
def parse_iso8601(timestamp_str):
"""Parse ISO 8601 timestamp to datetime object"""
return datetime.fromisoformat(timestamp_str.replace('Z', '+00:00'))
def calculate_merge_days(prs):
"""Calculate average days from creation to merge"""
merge_times = []
for pr in prs:
if pr.get('mergedAt'): # Only count merged PRs
created = parse_iso8601(pr['createdAt'])
merged = parse_iso8601(pr['mergedAt'])
days = (merged - created).days
merge_times.append(days)
if not merge_times:
return 0.0
avg = sum(merge_times) / len(merge_times)
return round(avg, 1) # Round to one decimal place
4. Top Contributor (Most PRs)
from collections import Counter
def get_top_contributor(prs):
"""Find author who opened the most PRs"""
authors = [pr['author']['login'] for pr in prs if pr.get('author')]
if not authors:
return None
author_counts = Counter(authors)
top_author, _ = author_counts.most_common(1)[0]
return top_author
Issue Metrics
1. Total Issue Count
total_issues = len(issues_data)
2. Bug Reports (label matching)
def count_bug_issues(issues):
"""Count issues with 'bug' in any label name"""
bug_count = 0
for issue in issues:
labels = issue.get('labels', [])
has_bug = any('bug' in label.get('name', '').lower() for label in labels)
if has_bug:
bug_count += 1
return bug_count
bug_count = count_bug_issues(issues_data)
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 · 29 tokens per session scan A 9af9eade1c24
github-metrics-processing is a skill published in the GitHub repository cxcscmu/SkillLearnBench (80 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,276 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.