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/update-prs/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/update-prs)<a href="https://agentmods.dev/skills/fastrepl/anarlog/update-prs"><img src="https://agentmods.dev/badge/skills/fastrepl/anarlog/update-prs/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/update-prs"><img src="https://agentmods.dev/badge/skills/fastrepl/anarlog/update-prs.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 | $0.00065 | $0.01062 |
| Opus 5.5 | $0.00026 | $0.00425 |
| Sonnet 5.5 | $0.00013 | $0.00212 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
update-prs 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 27d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update workspace PR titles and descriptions
Applicability
Use only in the Anarlog repository or its checkouts/worktrees when the active
checkout branch is exactly gitbutler/workspace. Before running this workflow,
check with git symbolic-ref --quiet --short HEAD (a read-only branch check).
On any other branch or detached HEAD, skip this skill and use the normal Git
workflow. Do not initialize GitButler or switch branches to activate the skill.
Use this checkout's skills, not a global copy or another checkout's skills.
Use this skill when asked to refresh active PR titles and descriptions in the Anarlog GitButler workspace.
Read the repository-local but skill and the active repository's AGENTS.md and workflow
skill when present. Use but to inspect workspace branches and stack
relationships, and the repository's preferred authenticated forge tools for PR
metadata. Derive the repository from the current workspace.
Invoking this workflow authorizes editing titles and descriptions of scoped PRs. Creating the skill alone does not execute it. Do not publish commits, create or merge PRs, change bases/draft state, or modify reviewers, labels or milestones.
Read the complete changes
- Read
but status --jsonand map applied branches to live open PRs by exact head repository and full branch name, including drafts. Exclude unrelated repository PRs and closed/merged PRs. Honor a narrower user selection and report ambiguous mappings rather than editing a guessed PR. - For each PR, retrieve its current title/body, base/head refs and SHAs,
complete commit list and full base-to-head diff. Paginate files and commits;
detect omitted/truncated patches and inspect those files through authenticated
repository contents or available
butinspection. Use the PR's actual base, which may be an earlier stack branch, not the workspace's combined diff. - Read all changed areas and relevant review fixes to understand the final implementation. Cover the entire PR, not just its latest commit, original description, or this chat's edits. In stacked PRs, describe the incremental contribution and material dependencies without claiming ancestors' work.
- Use published changes as the source of truth. Local-only fixes are not yet part of the PR; report that gap instead of describing them as shipped or pushing them during a metadata-only task. Record validation evidence with its SHA. Old CI or local workspace tests do not prove the current PR passed.
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.
- 27d ago First seen · 82 lines · 65 tokens per session scan A a3cb4005abf8
update-prs is a skill published in the GitHub repository fastrepl/anarlog (9,621 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,062 once invoked, about $0.0003 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 2026-10-02.
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.
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.
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.
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.
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…