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-mcp/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-mcp)<a href="https://agentmods.dev/skills/fastrepl/anarlog/release-mcp"><img src="https://agentmods.dev/badge/skills/fastrepl/anarlog/release-mcp/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-mcp"><img src="https://agentmods.dev/badge/skills/fastrepl/anarlog/release-mcp.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 | $0.00030 | $0.00474 |
| Opus 5.5 | $0.00012 | $0.00190 |
| Sonnet 5.5 | $0.00006 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
release-mcp 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 1mo 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.
What it actually says
Release MCP
Review every release. Inherit scope and session authorization from Release a New Version.
- Compare product changes with
apps/cli/src/mcp.rs,crates/api-cloud/src/mcp.rs,crates/mcp, sharedcrates/agent-access, and current contract tests. Review initialization, tools/resources, schemas, pagination, errors, capability exposure, and local/hosted differences. Derive expected tools from current source, never a remembered tool count. - Preserve local proposal-approval and hosted read-only boundaries, authentication, scopes, and workspace isolation. Implement required coverage before candidate freeze or document the intentional difference/explicit deferral. Do not infer supported agent behavior from the database schema alone.
- Run affected local and hosted contract/auth tests from
cli_ci.yamlandapi_ci.yaml, including allowed and denied paths. Reuse the CLI test evidence rather than rerunning identical shared checks. - For each shipped desktop platform, use the packaged CLI and isolated fixture
database for a real stdio initialize/discovery exchange and affected calls.
Keep stdout protocol-only and verify clean shutdown. Reuse the artifact and
verify-packaged-cli.pyevidence from Release CLI. - Publish required hosted changes through Release API. Verify the serving revision, authentication discovery/OAuth resource metadata, and authenticated discovery plus an affected operation with an authorized test account. Health/401 responses or mocks are not hosted runtime acceptance. Keep writes confined to supported local disposable fixtures and approval rules.
- Review shared host manifests/setup references once via Agent packages. Update public setup instructions through Release Docs.
Return local and hosted revisions, contract decisions, protocol/auth evidence, package publication or reuse, and unavailable credentials or runtime checks.
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.
- 1mo ago First seen · 40 lines · 30 tokens per session scan A 9fca3699d5a4
release-mcp is a skill published in the GitHub repository fastrepl/anarlog (9,621 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 474 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
testing-rules
Testing standards — frameworks, the testable-logic trigger, golden/snapshot rules, mocking rules, and the test-author → testing-reviewer pipeline. Load for /add-tests and any change that touches testable logic.
author-contract
Shared write-side contract every domain AUTHOR imports — smallest-diff implementation, ground-first, validation gates, tests-are-blocking, and never-approve-your-own-work. The write-side mirror of token-efficiency. Load at the start of any implementation task.
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.
run-wenlan-app
Build, launch, screenshot, and drive the wenlan-app Tauri desktop app in dev mode on macOS (WKWebView) or Windows (WebView2). Use when asked to run or start the app, verify a UI change in the real running app (not just tests), or take a screenshot of it.
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.