Classify Media Relevance
Decide whether an image or video found on a release page is editorial content (screenshots, demos, diagrams, product shots) or site chrome (avatars, logos, tracking pixels, decorative badges). Used during parsing to populate a release's media array.
Maintaining Orgs
>
Seeding Playbooks
Coordinate bulk playbook writing using parallel sub-agents — covers org discovery, prompt templates, model selection, batch dispatch, verification, and the parent-saves pattern for working around subagent permission limits. Currently wired up for Claude Code's Agent tool; the managed-agent fleet supports sub-agents too and the pattern can be adapted, but isn't wired up there yet.
Analyzing Releases
>
Releases Cli
Use the `releases` CLI to search, browse, and read the Releases.sh changelog registry from the terminal — the keyless, agent-friendly peer of the Releases MCP. Activate when the user mentions "releases CLI", runs a `releases` command, asks how to install it, or wants to look up releases, sources, orgs, collections, or changelogs from a shell.
Managing Sources
How to add, remove, list, validate, and manage changelog sources — covers ignored/blocked URLs, duplicate detection, and the validation workflow
Regenerating Overviews
>
Analyzing Releases
>
Grouping Releases
>
Finding Changelogs
How to find, evaluate, and recommend the best ingestion method for changelog URLs — covers feed discovery, provider detection, GitHub API, markdown sources, and scraping fallback
Generating Release Content
>
Creating Releases Json
>-
Parsing Changelogs
How the Releases fetch and parse pipeline works — covers feed vs scrape adapters, incremental vs bulk parsing, dry-run testing, crawl mode, content hashing, and enrichment
Releases Mcp
Use when the user asks about recent releases, changelogs, what's new in a library, breaking changes, version updates, or wants to compare products. Activates for questions like "what changed in Next.js 15?", "latest Tailwind releases", "compare Bun vs Deno releases".
Seeding Playbooks
Coordinate bulk playbook writing using parallel sub-agents — covers org discovery, prompt templates, model selection, batch dispatch, verification, and the parent-saves pattern for working around subagent permission limits. Local-only (Claude Code CLI) — managed agents do not yet support spawning sub-agents.
Github Screenshots
>-
Uploads
Lightweight upload gateway for agents. Upload screenshots during development to an R2 bucket and include image links in pull requests and comments.
Finding Changelogs
How to find, evaluate, and recommend the best ingestion method for changelog URLs — covers feed discovery, provider detection, GitHub API, markdown sources, and scraping fallback
Github Screenshots
>-
Uploads Cli
>-
Parsing Changelogs
How the Releases fetch and parse pipeline works — covers feed vs scrape adapters, incremental vs bulk parsing, dry-run testing, crawl mode, content hashing, and enrichment
Local Ingest
Onboard or backfill a company's changelog locally in Claude Code by fetching pages and extracting releases with the agent itself (and parallel sub-agents), then writing through the batch-upsert endpoint — no remote managed-agent session, no extraction inference billing. Use when you want to onboard a source without dispatching the MA, avoid the coordinator-Sonnet + worker-Haiku extraction loop, o…
Classify Media Relevance
Decide whether an image or video found on a release page is editorial content (screenshots, demos, diagrams, product shots) or site chrome (avatars, logos, tracking pixels, decorative badges). Used during parsing to populate a release's media array.
Managing Sources
How to create, delete, list, validate, and manage changelog sources — covers ignored/blocked URLs, duplicate detection, and the validation workflow
Backfilling Sources
Backfill a changelog source's full history locally in Claude Code via the backfill-source / backfill-sweep dynamic Workflows — preflight-gated, window-capped, budget-gated extraction written through the idempotent /batch upsert, with no managed-agent inference bill. Use when a source has a lot of history to pull in and dispatching the managed agent would be too expensive. Local Claude Code only.