regenerating-overviews

regenerating-overviews is a skill for Claude Code from buildinternet/releases. It costs 54 tokens per session (6,127 once invoked), scanned A, original, Apache-2.0.

A guide for creating or refreshing an organization’s AI-generated overview from recent release records. The overview is a short knowledge page about what the organization has shipped recently.

In plain words
What is it for?
Use it to rewrite one organization’s overview, refresh it after data changes, or generate overviews as part of a broader maintenance run.
Why use it?
It gives a repeatable refresh process after sources or release records change and avoids generating overviews for organizations marked as on-demand.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; mentions Claude Code.

Part of the registry-maintenance plugin — 8 skills shipped together

Good fit Use it to rewrite one organization’s overview, refresh it after data changes, or generate overviews as part of a broader maintenance run.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/buildinternet/releases/regenerating-overviews
Install

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.

Any agent
npx skills add buildinternet/releases --skill regenerating-overviews
Clone the repo
git clone --depth 1 https://github.com/buildinternet/releases

Made for: Claude Code.

Or install registry-maintenance, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

agentmods badge for regenerating-overviews

README.md
[![agentmods](https://agentmods.dev/badge/skills/buildinternet/releases/regenerating-overviews/github.svg)](https://agentmods.dev/skills/buildinternet/releases/regenerating-overviews)
Your own site
<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.

agentmods 80×15 button for regenerating-overviews

Your own site · 80×15
<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>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,127 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash 3521013193af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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
.claude/skills/regenerating-overviews/SKILL.md · 296 lines

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-orgs batch 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 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 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
}

Read the full file on GitHub · 296 lines

Changes

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.

  1. 8d ago First seen · 296 lines · 54 tokens per session scan A 3521013193af

Subscribe to this mod's changes

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.

Related

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.

librefang/librefang-registry · 37 tokens

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…

buildinternet/releases-cli · 86 tokens

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".

buildinternet/releases-cli · 64 tokens

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…

buildinternet/releases-cli · 75 tokens

graphql-expert

GraphQL expert for schema design, resolvers, subscriptions, and performance optimization.

librefang/librefang-registry · 19 tokens

openapi-expert

OpenAPI/Swagger expert for API specification design, validation, and code generation.

librefang/librefang-registry · 20 tokens