Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/buildinternet/releasesnpx agentmods add skills/buildinternet/releases/generating-release-contentWrote 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/generating-release-content)<a href="https://agentmods.dev/skills/buildinternet/releases/generating-release-content"><img src="https://agentmods.dev/badge/skills/buildinternet/releases/generating-release-content/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/generating-release-content"><img src="https://agentmods.dev/badge/skills/buildinternet/releases/generating-release-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Privilege Escalation · line 171 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Prompt Injection · line 93 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Data Exfiltration · line 170 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 | $0.00143 | $0.04596 |
| Opus 5.5 | $0.00057 | $0.01838 |
| Sonnet 5.5 | $0.00029 | $0.00919 |
| Haiku 4.5 | $0.00014 | $0.00460 |
Grade A, and why
generating-release-content scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Do not run `releases admin release update` or curl PATCH — the parent writes. How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generating Release Content
Populate the four AI-generated fields on a release:
title_generated— self-contained news headline (60–90 chars, hard cap 100)title_short— Axios "smart brevity" headline for chrome-stripped surfacessummary— 1–2 sentence prose blurbcomposition—{bugs, features, enhancements}counts (stored onreleases.metadata.$.composition)
The fields are the same whether you're generating for the first time or rewriting after a prompt change. There is no "new vs. regen" branch in the pipeline — last write wins.
The production prompt emits two more tags this skill does not persist. Since #1696 the shared prompt also outputs <breaking> (upgrade-risk verdict: major/minor/none/unknown) and <migration> (≤3-sentence upgrade steps), persisted at ingest to releases.breaking / releases.migration_notes. The write paths this skill uses can't carry them: PATCH /v1/releases/:id is .strict() and rejects breaking/migrationNotes, and the bulk script's UPDATE only sets the four fields above. Parse and discard them locally (they'll appear in the raw output); regenerating them is ingest-only for now.
Prompt is canonical in code, not in this skill
The system prompt and all parsing rules live in packages/ai/src/release-content.ts. Read it directly; do not paraphrase it back into the user message. The same module is consumed by the ingest worker (apps/api/src/workflows/poll-and-fetch.ts), the backfill script (scripts/generate-release-content.ts, OpenRouter by default), and this skill, so any drift between local-agent output and ingest-time output starts there.
Re-export from that file:
SYSTEM_PROMPT— pass verbatim as the system message, withcache_control: { type: "ephemeral" }buildReleaseBlock(input)— build the user message body from aSummarizeReleaseInput(org slug, source name, product name, title, version, url, content)isEmptyContent(body)— short-circuit boilerplate-only bodies; skip the model and write NULLsparseReleaseContent(text)— pull<title>,<title_short>,<summary>,<composition>(plus<breaking>/<migration>, which this skill's write paths drop — see above) out of a responseMODEL(claude-haiku-5-5— Anthropic fallback /--anthropic*paths only),MAX_OUTPUT_TOKENS(440),MAX_BODY_CHARS(8000). Haiku 5.5 calls omittemperature/top_p/top_kand sendthinking: { type: "disabled" }so the output cap is not spent on reasoning. Live summarize + the backfill script default to OpenRouterdeepseek/deepseek-v4.1-flash(SUMMARIZE_MODEL/RELEASE_CONTENT_MODEL).
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.
- 11d ago Changed 909f71a80221
- 26d ago Changed 7cd9208ab378
- 1mo ago Changed 466d47dc566c
- 1mo ago First seen · 273 lines · 143 tokens per session scan A 0e771c76d6a8
generating-release-content is a skill published in the GitHub repository buildinternet/releases (9 stars, last pushed today), licensed Apache-2.0. It adds 143 tokens to every session and 4,596 once invoked, about $0.0006 per session on Opus 5.5. 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
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".
releases-cli
Use the releases CLI to search, browse, and read the Release Notes Index 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, wants to look up releases, sources, orgs, collections, or changelogs from a…
github-cli
A command-line tool connection for GitHub tasks that built-in tools do not cover. It uses GitHub's command-line program to work with issues, pull requests, releases, workflows, searches, and the GitHub API.
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…
pre-release
Runs the pre-release checklist. Sets the readme.txt Stable tag to the version being released, captures every page type (sitemaps, robots, feeds, and the rest of the catalog), and flicks all buttons that the changelog mentions. Use when preparing a release, shipping a WordPress.org update, or when the user asks for the…
release-checklist
Walk the release checklist before tagging and publishing a version.