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 skills add buildinternet/releases --skill creating-releases-jsongit clone --depth 1 https://github.com/buildinternet/releasesWrote 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/buildinternet/releases/creating-releases-json)<a href="https://agentmods.dev/skills/buildinternet/releases/creating-releases-json"><img src="https://agentmods.dev/badge/skills/buildinternet/releases/creating-releases-json/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/buildinternet/releases/creating-releases-json"><img src="https://agentmods.dev/badge/skills/buildinternet/releases/creating-releases-json.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 | $0.00184 | $0.03846 |
| Opus 5 | $0.00092 | $0.01923 |
| Sonnet 5 | $0.00037 | $0.00769 |
| Haiku 4.5 | $0.00018 | $0.00385 |
Grade C, and why
creating-releases-json scanned grade C with 2 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 9d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://{domain}/.well-known/releases.json | node <skill-dir>/scripts/validate.mjs /dev/stdin Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://{domain}/.well-known/releases.json | node <skill-dir>/scripts/validate.mjs /dev/stdin How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating a releases.json manifest
releases.json is a small, owner-declared file that states what products a
company ships and where it publishes release notes — a changelog, an updates
page, an RSS/Atom feed, GitHub Releases, an App Store listing, or a hosted
CHANGELOG file. Any registry or agent that reads the format (starting with
releases.sh) learns where the release notes live directly
from the owner instead of guessing.
Authority comes from where the file lives, not from what it claims. A file at
https://{domain}/.well-known/releases.json speaks for that whole company; a
releases.json at a repository root speaks only for that repo. That is the entire
trust model — if you can publish the file at the URL, you can declare what it says.
Your job with this skill: figure out which scope applies, discover the locations where release notes actually live (never invent them), model the company's products without over-fragmenting, write a correctly-shaped file, validate it, and help get it published.
How you'll be asked to run this
Most of the time there is no codebase — someone just says "here's our website, make us a releases.json". That's the primary path: you work from the live site (and GitHub org), browsing to find where updates are published, and you hand back a finished file plus instructions on where to host it. You cannot commit it for them.
Less often you're working inside a repo — the one that serves the company's site, or a single product/library repo — in which case you can also read the codebase and write the file into place. Both paths use the same steps below; only Step 1 (scope) and Step 5 (publish) differ.
The one rule that matters most
Only declare locations that really exist and respond. The manifest states plain facts about where updates are published. A guessed or aspirational URL is worse than omitting it — it creates a broken source. Before writing any locator, confirm the URL resolves (fetch it, or check it against the codebase/site). If you cannot verify a location, leave it out and say so.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 273 lines · 184 tokens per session scan C a5bffb0dacd9
creating-releases-json is a skill published in the GitHub repository buildinternet/releases (6 stars, last pushed 6d ago), licensed Apache-2.0. It adds 184 tokens to every session and 3,846 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
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…
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".
changelog-generator
Generate a polished CHANGELOG.md and release-notes.md from a local git repository (or a captured .git-log.txt dump). Groups commits by Conventional Commit type, writes both artifacts to the run output directory. Use when asked to draft release notes, summarize commits between tags, or produce a human-readable…
release-checklist
Walk the release checklist before tagging and publishing a version.
changelog-generator
Transform technical git commits into polished, user-friendly changelogs and release notes. Automatically categorizes changes, translates developer language into customer-friendly copy, and generates professional changelog entries.
release-readiness
Use this skill when preparing a tag, package, deployment, or public release.