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/prisma/prisma-next/draft-release-notesnpx skills add prisma/prisma-next --skill draft-release-notesgit clone --depth 1 https://github.com/prisma/prisma-nextWrote 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/prisma/prisma-next/draft-release-notes)<a href="https://agentmods.dev/skills/prisma/prisma-next/draft-release-notes"><img src="https://agentmods.dev/badge/skills/prisma/prisma-next/draft-release-notes.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 | $0.00154 | $0.05136 |
| Opus 5 | $0.00077 | $0.02568 |
| Sonnet 5 | $0.00031 | $0.01027 |
| Haiku 4.5 | $0.00015 | $0.00514 |
Grade A, and why
draft-release-notes 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 2d 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.
This is a copy
92% identical to draft-release-notes — 76 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft release notes
This skill fires inside a stable-release cut. The release-cutting agent runs it from the release/<version> worktree that publish-npm-version created, with the target version already known, and produces the committed notes file that is the GitHub Release body (the publish workflow ships it verbatim via gh release create --notes-file docs/releases/v<version>.md). There is no --generate-notes fallback — the file you author here is what every consumer reads.
The skill is prose-driven: there is no codemod or script to run. You — the agent — do the enumeration, the Linear-context lookup, the triage, and the writing directly, the same way record-upgrade-instructions walks you through authoring an upgrade entry rather than running one for you.
When to use
Run this skill when all of the following hold:
- A stable (
latest) release is being cut — the target version$NEXTis known (computed bypublish-npm-versionstep 1, e.g.0.12.0). - You are in the
release/<version>worktree checked out at the bump commit (HEAD carries the bumped rootversion). docs/releases/v$NEXT.mddoes not exist yet (the PR-mode release-notes gate,pnpm check:release-notes --mode pr, fails the release PR until it does).
Do not run it for -dev.N or -beta.N builds: those create no GitHub Release and are not gated. Do not run it to backfill notes for an already-shipped release — the convention starts from the first release cut after it landed.
The two hard rules
These are project requirements, not style preferences. A draft that violates either is wrong even if everything else is perfect.
Rule 1 — Never copy Linear content verbatim
Linear is a summarization-context input only. You read a ticket to understand the user-facing outcome of an opaque PR title, then you write a fresh, public, user-facing sentence describing that outcome. You never paste ticket prose into the notes. Specifically, the following must never appear in docs/releases/*.md or CHANGELOG.md:
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.
- 2d ago First seen · 303 lines · 154 tokens per session scan A baaffa1d7795
draft-release-notes is a skill published in the GitHub repository prisma/prisma-next (419 stars, last pushed 11d ago), licensed Apache-2.0. It adds 154 tokens to every session and 5,136 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to draft-release-notes, differing in 76 lines, and is treated as a copy.
Other skills, from other repositories
draft-release-notes
Author the committed release-notes file for a Prisma 8 release (stable or 8.0.0-rc.N) by enumerating the merged PRs since the previous release v tag (stable or -rc.N), resolving opaque TML-NNNN: titles via Linear context (never copied verbatim), triaging public-worthiness, and writing categorized notes — breaking…
publish-npm-version
Cuts the next release of Prisma 8: bumps the root package.json version (on the v8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every workspace package, and opens a PR titled "chore(release): bump to ". When the maintainer merges the PR, the Publish to npm workflow runs automatically and ships the new version to npm…
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
record-upgrade-instructions
Record upgrade instructions alongside a Prisma Next breaking-change PR, so downstream consumers (users of @internal/ and authors of Prisma Next extensions) can apply the matching code translation automatically via the published upgrade skills. Use when you have refactored framework code and the test suite went red in…
triage-contributor-pr
Triage open pull requests from external contributors to prisma/prisma and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…
contrib-pr
Open a high-quality external contributor PR against prisma/orm. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.