anarlog: Skill for Claude Code

.agents/skills/new-changelog/SKILL.md

new-changelog is a skill for Claude Code, Codex from fastrepl/anarlog. It costs 24 tokens per session (1,058 once invoked), scanned C, original, MIT.

A release-writing helper for desktop software that creates the next Markdown changelog entry under packages/changelog/content. A changelog is a record of changes included in each software release.

In plain words
What is it for?
Use it when preparing the next desktop release note and creating the correctly named, dated, and summarized Markdown file.
Why use it?
It removes the need to determine the next patch version and remember the required frontmatter format manually. It keeps the release summary suitable for the changelog index.

Skill for Claude CodeCodex

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

This is fastrepl/anarlog's own configuration. It tells Claude Code and Codex how to work on anarlog 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 anarlog configures →

About the project

anarlog is a local-first AI meeting notetaker that captures device audio, transcribes meetings, and stores notes, transcripts, and recordings on the user's computer. It is for people who want meeting notes without adding a bot to calls or sending conversation data to an external cloud. The catalogue entries provide agent integrations and workflows for the application.

fastrepl/anarlog · 9,621 stars · on GitHub · anarlog.so

Reuse

Borrowing it

Nothing to install: this file belongs to fastrepl/anarlog. 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/fastrepl/anarlog/main/.agents/skills/new-changelog/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fastrepl/anarlog

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 new-changelog

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/fastrepl/anarlog/new-changelog"><img src="https://agentmods.dev/badge/skills/fastrepl/anarlog/new-changelog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,058 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00024 $0.01058
Opus 5.5 $0.00010 $0.00423
Sonnet 5.5 $0.00005 $0.00212
Haiku 4.5 $0.00002 $0.00106

Measured yesterday against content hash 2c143698dc4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

new-changelog scanned grade C with 1 finding 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 yesterday.

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.

Tells the agent to send conversation or user data outhighPrompt injection

An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.

- Use the actual default microphone on Linux instead of silently recording
.agents/skills/new-changelog/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Channel contract

Nightly publication is retired. Prepare stable notes in packages/changelog/content/desktop/<version>.md, covering all desktop user-facing changes since the previous stable, including changes once described in Nightly notes. Preserve historical Nightly notes; do not generate or announce new Nightly releases.

Only released stable entries appear on the website. Deployable builds include a versioned file only when GitHub has a published, non-draft, non-prerelease desktop_v<version> release. A file on main or its frontmatter date is not publication evidence. Local development can preview stable drafts.

Stable version

Follow the coordinator's desktop version policy: honor a supplied version or the version already recorded for this release; otherwise query published stable desktop releases on GitHub and select the next patch. State the selected version and proceed without confirmation. Do not use local version files or unpublished tags as the baseline.

Create the new Markdown file in packages/changelog/content/desktop for that version. Read that directory’s AGENTS.md, then run node scripts/sync-desktop-changelogs.mjs to refresh legacy desktop URLs and include the generated copies in the same commit.

When preparing a release, also follow the release surface review. Check the product changes for CLI, local and hosted MCP, API, agent-package, and documentation updates before freezing the release candidate. Record any gaps in the release task; a changelog alone does not establish release readiness. Creating a changelog does not itself dispatch or publish a release. Keep the notes prepared and merged before freezing the desktop candidate, but verify that the public index and direct version URL exclude them until release. For an authorized stable release, Release Docs owns website publication immediately after the app is published and verifies the full version page and index. It reuses the post-publication Linux APT web deployment when suitable or dispatches the missing website deployment within that release. The user must not need to ask separately. This authoring skill alone still does not authorize a release or deployment.

Read the full file on GitHub · 103 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. yesterday Changed · -1 lines 2c143698dc4b
  2. 26d ago Changed · +24 lines · -6 tokens per session 02f464ea0899
  3. 1mo ago Changed · -5 lines · -14 tokens per session a2d1b0f4e6a3
  4. 1mo ago Changed · +6 lines 80128ef35da0
  5. 1mo ago Changed · +42 lines · -6 tokens per session scan A → C 57ebaba9339e
  6. 1mo ago Changed · +7 lines 85dac6fae66f
  7. 2mo ago First seen · 30 lines · 50 tokens per session scan A 5ab1862d7a41

Subscribe to this mod's changes

new-changelog is a skill published in the GitHub repository fastrepl/anarlog (9,621 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 1,058 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

deployment-rules

Release/deployment standards — semantic-release, commitlint, version sync, the updater. Load for /prepare-release and changes to release.config.mjs / commitlint / workflows / version files. Owned by project-steward.

saeedkolivand/ai-job-hunter-app · 49 tokens

coding-standards

General repo rules enforced by ESLint/TypeScript/CI — PRs-only, never bypass lint, import ordering, type imports, path privacy, commit format. Load for any code change.

saeedkolivand/ai-job-hunter-app · 44 tokens

app-release

Use when the user asks to release a new version, ship a build, or publish a Skill Zoo release. Also use when a tag push results in Homebrew 404 errors or missing artifact failures.

luochang212/skill-zoo · 43 tokens

graphify-windows

Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPHREPORT.md.

saeedkolivand/ai-job-hunter-app · 75 tokens

lessons

How to propose and query distilled lessons (the experiential memory). Only project-steward persists; every other agent proposes/queries. Use when you discover a durable lesson or need prior experience for the current task.

saeedkolivand/ai-job-hunter-app · 45 tokens

npm-release

Use when publishing or preparing to publish an npm package from this repository, especially the Skill Zoo CLI package under packages/cli. Also use when npm publish fails because of duplicate versions, npm authentication, browser authentication, dist-tag propagation, tarball contents, bin entry issues, or…

luochang212/skill-zoo · 66 tokens