JETLS.jl: Skill for Claude Code

.agents/skills/changelog/SKILL.md

changelog is a skill for Claude Code, Codex from aviatesk/JETLS.jl. It costs 41 tokens per session (448 once invoked), scanned A, original, MIT.

A guideline for updating CHANGELOG.md, the file that records user-visible changes between releases. It defines where and how to record additions, changes, and fixes.

In plain words
What is it for?
Use it before committing new features, bug fixes, or behavior changes. Skip it for internal refactors, CI changes, documentation-only work, and minor dependency updates.
Why use it?
It keeps release notes consistent and makes user-facing changes easier to find. It also prevents changes from being committed without the required changelog entry.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is aviatesk/JETLS.jl's own configuration. It tells Claude Code and Codex how to work on JETLS.jl itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything JETLS.jl configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aviatesk/JETLS.jl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aviatesk/JETLS.jl/master/.agents/skills/changelog/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aviatesk/JETLS.jl

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 changelog

README.md
[![agentmods](https://agentmods.dev/badge/skills/aviatesk/jetls.jl/changelog/github.svg)](https://agentmods.dev/skills/aviatesk/jetls.jl/changelog)
Your own site
<a href="https://agentmods.dev/skills/aviatesk/jetls.jl/changelog"><img src="https://agentmods.dev/badge/skills/aviatesk/jetls.jl/changelog/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 changelog

Your own site · 80×15
<a href="https://agentmods.dev/skills/aviatesk/jetls.jl/changelog"><img src="https://agentmods.dev/badge/skills/aviatesk/jetls.jl/changelog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 448 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00041 $0.00448
Opus 5 $0.00020 $0.00224
Sonnet 5 $0.00008 $0.00090
Haiku 4.5 $0.00004 $0.00045

Measured 10d ago against content hash 608907764976, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

changelog 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 10d 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.

.agents/skills/changelog/SKILL.md · 56 lines

What it actually says

Updating CHANGELOG.md

Format

This project follows Keep a Changelog.

Line length

CHANGELOG.md is exempt from the 80-character Markdown line length rule because it is used for GitHub release notes, where hard line breaks disrupt rendering.

That said, do not put everything on a single line unconditionally. Break lines at natural points (sentence boundaries, after colons, etc.) when an entry is long enough to benefit from it. Short, single-sentence entries are fine as one line.

Section structure

New entries go under the ## Unreleased section. Use the following subsections as needed (in this order):

  • ### Announcement -- important notices (always first if present)
  • ### Added -- new features
  • ### Changed -- changes to existing functionality
  • ### Fixed -- bug fixes

Entry style

  • Start Added entries with "Added ..." and Fixed entries with "Fixed ...".
  • Changed entries typically start with the component name (e.g. "lowering/undef-local-var now ...").
  • When closing a GitHub issue, append (Closed https://github.com/aviatesk/JETLS.jl/issues/NNN).
  • Use backticks for diagnostic names, function names, and code elements.

Entry content

Write entries from the user's perspective. Describe what changed in terms of user-visible behavior — not implementation details.

  • Don't include internal mechanisms (AST node types, specific JuliaLowering/JuliaSyntax internals, traversal strategies) unless a user could reasonably observe or interact with them.
  • The "why" of a fix rarely matters to users; the "what" of the new behavior does. If the prior behavior is worth mentioning, describe its user-visible symptom, not its cause.
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. 10d ago First seen · 56 lines · 41 tokens per session scan A 608907764976

Subscribe to this mod's changes

changelog is a skill published in the GitHub repository aviatesk/JETLS.jl (308 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 448 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 2026-08-30.