skill-069

skill-069 is a skill for Claude Code, Codex from legendtkl/agentic-skill-router. It costs 28 tokens per session (1,662 once invoked), scanned A, original, MIT.

A set of templates and writing rules for pull request descriptions. Pull requests are proposed code changes that teammates review before they are added to a project.

In plain words
What is it for?
It helps write descriptions for new features, bug fixes, and code refactoring, including their scope, cause, testing, and compatibility details.
Why use it?
It removes the need to structure every pull request description from scratch and helps explain changes consistently.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit It helps write descriptions for new features, bug fixes, and code refactoring, including their scope, cause, testing, and compatibility details.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/legendtkl/agentic-skill-router/skill-069
Install

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.

Any agent
npx skills add legendtkl/agentic-skill-router --skill skill-069
Clone the repo
git clone --depth 1 https://github.com/legendtkl/agentic-skill-router

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for skill-069

README.md
[![agentmods](https://agentmods.dev/badge/skills/legendtkl/agentic-skill-router/skill-069/github.svg)](https://agentmods.dev/skills/legendtkl/agentic-skill-router/skill-069)
Your own site
<a href="https://agentmods.dev/skills/legendtkl/agentic-skill-router/skill-069"><img src="https://agentmods.dev/badge/skills/legendtkl/agentic-skill-router/skill-069/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.

agentmods 80×15 button for skill-069

Your own site · 80×15
<a href="https://agentmods.dev/skills/legendtkl/agentic-skill-router/skill-069"><img src="https://agentmods.dev/badge/skills/legendtkl/agentic-skill-router/skill-069.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,662 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.01662
Opus 5 $0.00014 $0.00831
Sonnet 5 $0.00006 $0.00332
Haiku 4.5 $0.00003 $0.00166

Measured 6d ago against content hash 614d9091a2df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

skill-069 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 6d 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.

experiments/dci-compare/skillrouter-skills/skill-069/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Description Template Skill

This skill provides everything needed to write high-quality PR descriptions: templates, format specifications, and examples.

Quick Reference

Command Description
/pr-description-template Show available templates and help
/pr-description-template feature Example PR for new feature implementations
/pr-description-template bugfix Example PR for bug fixes
/pr-description-template refactor Example PR for refactoring/architectural changes
/pr-description-template format Show complete PR description format

Available Templates

Template Use For Characteristics
feature New functionality, APIs, components Emphasizes scope, design decisions, future work
bugfix Bug fixes, regressions, hotfixes Emphasizes root cause, testing, before/after
refactor Architectural changes, code restructuring Emphasizes compatibility, migration, incremental changes

Template Selection Guide

Choose feature when:

  • Adding new functionality (greenfield development)
  • Implementing new APIs, services, or components
  • Adding new user-facing features
  • Introducing new capabilities to the codebase

Choose bugfix when:

  • Fixing a bug of any size
  • Addressing regressions
  • Hotfixes for production issues
  • Correcting unexpected behavior

Choose refactor when:

  • Making architectural changes
  • Restructuring code without changing behavior
  • Reorganizing modules or file structure
  • Implementing breaking changes with migration
  • Improving code quality without adding features

PR Description Format

Every PR description MUST follow this structure. This is the canonical format for all pull requests.

Required Sections

## Summary

<High-level summary of changes and context for why the changes were made.
Should answer: What does this PR do? Why is it needed?
Keep to 2-4 sentences. Focus on business value and user impact.>

## What's Included

<Compact list organized by category to help reviewer understand scope at a glance>

**Source Code:**
- `path/to/file.py` - Brief description of change

**Tests:**
- `tests/test_file.py` - What's being tested

**Documentation:**
- `docs/file.md` - What was documented (or note if missing)

**Configuration:**
- `pyproject.toml` - Dependencies added/changed

## Key Design Decisions

<Design decisions to document for reviewer context.
Focus on "why this approach" not implementation details.
Number each decision for easy reference in review comments.>

1. **Decision Title**: Rationale for why this approach was chosen over alternatives

2. **Convention Deviation** (if any): Any intentional deviations from development-conventions with justification

## Critical Areas for Review

<Prioritized areas deserving careful review.
Help reviewer focus their attention on what matters most.
Include line numbers when specific ranges need attention.>

1. **`path/to/critical/file.py:L10-L50`** - Description of why this needs careful review (e.g., complex logic, security implications, breaking change)

2. **`path/to/another/file.py`** - Why this is important to review

Read the full file on GitHub · 251 lines

Changes

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.

  1. 6d ago First seen · 251 lines · 28 tokens per session scan A 614d9091a2df

Subscribe to this mod's changes

skill-069 is a skill published in the GitHub repository legendtkl/agentic-skill-router (5 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 1,662 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 2026-09-03.