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 skills/buildinternet/releases/finding-changelogsnpx skills add buildinternet/releases --skill finding-changelogsgit 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/finding-changelogs)<a href="https://agentmods.dev/skills/buildinternet/releases/finding-changelogs"><img src="https://agentmods.dev/badge/skills/buildinternet/releases/finding-changelogs.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.04125 |
| Opus 5 | $0.00019 | $0.02063 |
| Sonnet 5 | $0.00008 | $0.00825 |
| Haiku 4.5 | $0.00004 | $0.00413 |
Grade A, and why
finding-changelogs 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finding Changelogs
Determine the best way to get structured release data from a changelog or release notes page.
Many pages have better-structured data sources behind them — RSS feeds, raw markdown files, or API endpoints. Finding those avoids the complexity of parsing rendered HTML.
Content Verification
After discovering a feed or structured source, always spot-check the entries before accepting it. Sample a few entries and verify they are actual changelog or release content — not blog posts, marketing articles, tutorials, or unrelated editorial content.
Red flags that a feed is wrong:
- Entry URLs point to
/blog/paths rather than/changelog/or/releases/paths - Titles read like articles or tutorials (e.g., "Choosing a logging library: The definitive guide")
- No version numbers, semver patterns, or feature/fix language anywhere in the entries
- The feed URL is site-wide (e.g.,
/feed.xml) rather than section-specific (e.g.,/changelog/feed.xml) - Entry content discusses opinions, comparisons, or industry trends rather than product changes
If the entries don't look like releases, the feed is likely the wrong one. Look for a more specific feed, or fall back to a different ingestion method.
Watch for redirects. A URL like blog.example.com/changelog/ may redirect to example.com/changelog/, but feed discovery may have already found the blog's site-wide feed before the redirect. Always check whether the discovered feed is scoped to the changelog section, not the entire site.
Priority Order
Well-known files > Link relations > Feeds > GitHub Releases API > raw markdown > page scraping.
For github sources, the fetch pipeline ingests tagged releases and the repo's canonical CHANGELOG.md (or CHANGES.md / HISTORY.md / RELEASES.md / NEWS.md at the repo root) on every fetch pass — the file is surfaced in the web UI as a separate tab, embedded on demand by the get_catalog_entry MCP tool, and is often the richer source when a project ships entries that never became tagged releases. The refresh piggybacks on each GitHub fetch with a content-hash short-circuit, so stored files stay in sync with tagged releases. You don't need to add a second source for the CHANGELOG file; the github adapter handles both.
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.
- 5d ago First seen · 266 lines · 39 tokens per session scan A 482701276377
finding-changelogs is a skill published in the GitHub repository buildinternet/releases (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 39 tokens to every session and 4,125 once invoked, about $0.0002 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 skills, from other repositories
xquik-social-data
Use Xquik for X and Twitter social data workflows through its public API, SDKs, MCP server, webhooks, and installable agent skill.
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".
analyzing-releases
Analyze release trends across multiple companies to produce competitive intelligence. Use when asked to compare companies, analyze a market segment, identify industry trends, forecast upcoming releases, or answer questions like "what is X shipping lately" or "how does X compare to Y." Also triggers on requests for…
graphql-expert
GraphQL expert for schema design, resolvers, subscriptions, and performance optimization.
openapi-expert
OpenAPI/Swagger expert for API specification design, validation, and code generation.