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.
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.
curl -O https://raw.githubusercontent.com/fastrepl/anarlog/main/.agents/skills/release-docs/SKILL.mdgit clone --depth 1 https://github.com/fastrepl/anarlogWrote 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.
[](https://agentmods.dev/skills/fastrepl/anarlog/release-docs)<a href="https://agentmods.dev/skills/fastrepl/anarlog/release-docs"><img src="https://agentmods.dev/badge/skills/fastrepl/anarlog/release-docs/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.
<a href="https://agentmods.dev/skills/fastrepl/anarlog/release-docs"><img src="https://agentmods.dev/badge/skills/fastrepl/anarlog/release-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.01376 |
| Opus 5.5 | $0.00014 | $0.00550 |
| Sonnet 5.5 | $0.00007 | $0.00275 |
| Haiku 4.5 | $0.00003 | $0.00138 |
Grade A, and why
release-docs 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 26d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Docs
Review every release. Inherit scope and session authorization from Release a New Version. Own documentation and changelog publication through completion, not just the source file or PR. For mobile-only distribution, prepare Mobile notes and review affected mobile and shared documentation. Use the Mobile publication steps below; desktop release/tag checks are not applicable.
Before candidate freeze
- Read
docs/AGENTS.mdand New Changelog. Compare all user-facing changes since the previous published release in that stream (previous stable for stable notes) withpackages/changelog/content/<stream>/<version>.md,docs/,docs/docs.json, andapps/web/public/llms.txt. Cover guides, installation/upgrade instructions, CLI/MCP/API examples, screenshots, troubleshooting, and platform availability. Preserve external-contributor credits and describe shipped behavior only. - Prepare the changelog with its
dateand plain-textsummary. Run changed-file formatting,pnpm -F @anlg/changelog typecheck, and affected web checks fromweb_ci.yaml/rootAGENTS.md. For docs, use the Mintlify version pinned incli_ci.yamlto runvalidateandbroken-links --check-anchors --check-redirectsfromdocs/; preview affected pages and navigation. Coordinate public skill changes with Agent packages. - Merge required content before freezing the candidate. Keep unreleased
notes hidden: desktop entries require published, non-draft, non-prerelease
GitHub
desktop_v<version>releases; mobile entries require verified adjacent publication records as specified inpackages/changelog/content/mobile/AGENTS.md. Verify the production index omits the candidate and its direct URL returns 404 before publication. A local production build can test this;vite devintentionally previews drafts.
Publish with the app
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.
- 26d ago Changed · +23 lines d4511804fe3d
- 1mo ago First seen · 80 lines · 34 tokens per session scan A 917b561032a8
release-docs is a skill published in the GitHub repository fastrepl/anarlog (9,621 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,376 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-21.
Other skills, from other repositories
resume-export-standards
ATS-safe + accessible resume/CV export standards (PDF/DOCX) — real ATS parsing limits, single-column rules, document-metadata accessibility (full PDF/UA-1 tagging is a future goal), country/industry CV norms (US/UK/DE), keyword hygiene. Load for changes under export/, model/, theme/, templates/, locale/, fonts…
job-match-standards
How real ATS (Workday/Greenhouse/Lever/Taleo/iCIMS/Ashby) parse, score and rank in 2026; evidence-based matching; and the legal limits on automated screening (EU AI Act high-risk, NYC LL144, EEOC Title VII, GDPR Art. 22). Load for changes under commands/matchresume.rs, coverletter.rs, validate/, documents/embed.
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.
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.
presentations
Build PowerPoint (PPTX) decks — pptxgenjs when Node is present, python-pptx when not; edit existing decks in place via OOXML — with visual QA before delivery.
spreadsheets
Build Excel (XLSX) workbooks with openpyxl and edit existing ones through headless LibreOffice Calc — live formulas, number formats, layout — recalculated and re-inspected before delivery.