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-api/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-api)<a href="https://agentmods.dev/skills/fastrepl/anarlog/release-api"><img src="https://agentmods.dev/badge/skills/fastrepl/anarlog/release-api/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-api"><img src="https://agentmods.dev/badge/skills/fastrepl/anarlog/release-api.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 | $0.00027 | $0.00717 |
| Opus 5.5 | $0.00011 | $0.00287 |
| Sonnet 5.5 | $0.00005 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
release-api 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 API
Review every release, including client-only changes. Inherit scope and session authorization from Release a New Version.
-
Compare changed product behavior and each service's live source SHA against
apps/api,apps/stripe,crates/api-cloud, affected auth/sync/proxy crates,supabase/,apps/api/openapi.gen.json, andpackages/api-client/src/generated. Check auth, scopes, payloads/errors, pagination, data compatibility, and existing client behavior. Record required changes, concrete reuse reasons, or explicit deferrals before freezing the candidate. -
Read
api_ci.yaml,api_cd.yaml,db_ci.yaml, anddb_cd.yamlplus the affected component instructions. Run the full locally reproducible affected jobs and consumer checks. For contract changes, run:cargo test -p api gen_openapi_json pnpm -F @anlg/api-client openapi pnpm -F @anlg/api-client typecheckUse owning generators and verify repeated generation is stable. Test hosted migrations/RLS in an isolated local Supabase stack, never against production.
-
Inspect current service choices and live configuration before deploying. Core, AI, Sync, Gateway, and billing have independent deployment decisions. The billing API and
apps/stripeship together viaapi_cd.yamlwithservice=billing. Do not treat a shared API version/tag as proof every service runs that source. Hosted Postgres has its owndb_cd.yamldeployment history. -
Deploy required backward-compatible hosted changes before dependent desktop or mobile clients. Select the exact approved environment, service and merged source. Use
gh workflow run api_cd.yaml --ref main -f service=<service>andgh workflow run db_cd.yaml --ref mainas appropriate, after reading their current inputs. Verify each run'sheadSha; never ship the combined GitButler workspace. Include every dependency in filtered Docker build contexts. -
Follow deployments to terminal success. Confirm actual serving source/digest, version and role-specific readiness, then exercise affected authenticated behavior with an authorized test account.
/health, an unauthenticated401, or one healthy role does not prove other roles or operations work. Coordinate hosted protocol checks with Release MCP. -
For schema changes, record the selected hosted project, applied migrations, source/run and compatibility checks. Keep shipped SQLite migrations append-only, desktop/mobile schemas compatible, and older clients supported. Follow current drain, migration, continuity, and recovery requirements; successful health checks alone do not establish zero downtime.
Return generated-contract decisions, candidate CI, each service/database's deployed revision and run URL, live evidence, or reuse reason and outstanding work. Reuse a live deployment only when its source includes the required changes; no artificial version bumps or no-op redeploys. Website and Mintlify publication belong to Release Docs, not the API deploy.
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 · 58 lines · 27 tokens per session scan A 49748c94d7a0
release-api is a skill published in the GitHub repository fastrepl/anarlog (9,621 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 717 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
automation-standards
Scraping + AI-provider standards — the Scraper trait & SCRAPERS registry, selector resilience, rate-limiting/cancellation, and the provider-abstraction (zero-change) rule for embeddings/streaming/prompts. Load for changes under scraping/, aiprovider/, packages/prompts, documents/embed.
rust-standards
Rust/Tauri backend standards — L0–L3 layers, centralized platform/net/error ownership, Rust-first business logic, registries, error handling. Load for changes under apps/desktop/src-tauri/src/.
tauri-standards
Tauri shell standards — the IPC 5-step capability flow, command implementation pattern, and capability/permission wiring. Load for new IPC capabilities and changes to commands.rs / tauri-client.ts / capabilities/.
webapp
Use for fullstack web apps built with the bundled Express, Vite, React, Tailwind, and Drizzle template.
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.