Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/buildinternet/releases-cli/releasesgit clone --depth 1 https://github.com/buildinternet/releases-cliWhat 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 | $0.00008 | $0.00284 |
| Opus 5 | $0.00004 | $0.00142 |
| Sonnet 5 | $0.00002 | $0.00057 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
releases 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 3d 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
/releases
Search changelogs and release notes from the Releases.sh registry.
Usage
/releases <product> [query]
/releases --compare <product1> <product2>
- product: A product name, org name, or slug (e.g., "next.js", "tailwind", "vercel")
- query: What you're looking for (optional but recommended for targeted results)
- --compare: Compare recent release activity between two products
Examples
/releases next.js
/releases tailwind v4 breaking changes
/releases prisma migration guide
/releases --compare bun deno
/releases vercel last 7 days
How It Works
- Searches
list_organizationsto resolve the product name to a known org or product - If a query is provided, uses
searchwithtype: ["releases"]filtered to that org - If no query, uses
get_latest_releasesto show the most recent entries - With
--compare, usesget_latest_releaseson both product slugs and synthesizes the comparison - Results include version numbers, dates, and key changes from release notes
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.
- 3d ago First seen · 38 lines · 8 tokens per session scan A c0d8b92424df
releases is a command published in the GitHub repository buildinternet/releases-cli (4 stars, last pushed 3d ago), licensed MIT. It adds 8 tokens to every session and 284 once invoked, about $0.0000 per session on Opus 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 2026-08-31.
Other commands, from other repositories
discover-changelog
Given a company name or domain, find their changelog/release-note sources, add them to Releases, and fetch recent entries. This is the manual, Claude-driven onboarding flow — it uses the releases CLI against the production API and does not dispatch to managed agents. (If you want managed-agent onboarding, use releases…
review-renovate
Review and merge renovate PRs with automerge configuration updates.
release
Perform a full release: generate release notes, bump version, commit, tag, and push.
release
Create a full stable release for the project. Optionally pass a title suffix (e.g., "Template Presets Fix") or extra notes.
release
This compatibility command keeps /oh-my-claudecode:release available without loading the full release skill description in every Claude Code session.
release
The pre-tag controller: version sync, changelog, clean tree, gate, and suite — every failure listed, the tag printed, never run.