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 regenerating-overviewsgit 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/regenerating-overviews)<a href="https://agentmods.dev/skills/buildinternet/releases/regenerating-overviews"><img src="https://agentmods.dev/badge/skills/buildinternet/releases/regenerating-overviews/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/regenerating-overviews"><img src="https://agentmods.dev/badge/skills/buildinternet/releases/regenerating-overviews.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 256 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00054 | $0.06127 |
| Opus 5 | $0.00027 | $0.03063 |
| Sonnet 5 | $0.00011 | $0.01225 |
| Haiku 4.5 | $0.00005 | $0.00613 |
Grade A, and why
regenerating-overviews scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> **Sandbox without a working CLI?** In an environment where the compiled `releases` binary can't reach the API through a TLS-intercepting egress proxy (e.g. the weekly SANA sandbox), skip the CLI and hit the REST routes How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Regenerating Overviews
Org overviews are short knowledge pages summarizing what an org has shipped recently. Regeneration is agent-driven: this skill carries the prompt and structure rules; the API exposes a pure-data input builder and a dumb upsert.
No managed-agent task exists for this today. You — the Claude Code instance reading this skill — are the agent. The CLI is a thin client.
When to Use
- Single org refresh: "regenerate the vercel overview"
- Inside
maintaining-orgsbatch runs: each per-org sub-agent runs this skill - After significant source mutations: a new active source landed, an old one was hidden
- After backfilling a window of releases: stale overview no longer reflects current focus
Skip on-demand orgs. If org.discovery === 'on_demand', do not regenerate — the API-side overview workflow already gates on this column, and generating an overview for an org that hasn't been curated wastes tokens. The releases admin overview plan / overview list endpoints already filter to curated orgs server-side via the organizations_active view, so manifest-driven sweeps don't need a separate filter pass.
Workflow
Three steps. Each step is a single CLI invocation; no other tools needed.
Sandbox without a working CLI? In an environment where the compiled
releasesbinary can't reach the API through a TLS-intercepting egress proxy (e.g. the weekly SANA sandbox), skip the CLI and hit the REST routes directly — see Running without the CLI (curl fallback). Same three steps, same contracts.
1. Fetch inputs
releases admin overview inputs <slug> --json [--window 30]
Returns:
{
"org": { "id", "slug", "name", "description" },
"sources": [{ "id", "slug", "name", "type" }, ...], // active only
"existingContent": "...prior overview body..." | null,
"selected": [{ ...Release }, ...], // post-selection
"totalAvailable": 47, // pre-cap count
"windowDays": 30 // 30d default; widens to 90d
// when the org shipped fewer
// than 5 releases in 30d
}
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.
- 8d ago First seen · 296 lines · 54 tokens per session scan A 3521013193af
regenerating-overviews is a skill published in the GitHub repository buildinternet/releases (6 stars, last pushed 5d ago), licensed Apache-2.0. It adds 54 tokens to every session and 6,127 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (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
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.