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/justrach/codegraff2/write-release-notesnpx skills add justrach/codegraff2 --skill write-release-notesgit clone --depth 1 https://github.com/justrach/codegraff2What 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 | $0.00105 | $0.01328 |
| Opus 5 | $0.00053 | $0.00664 |
| Sonnet 5 | $0.00021 | $0.00266 |
| Haiku 4.5 | $0.00011 | $0.00133 |
Grade A, and why
write-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 yesterday.
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
100% identical to write-release-notes — 0 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Release Notes
Generate clear, informative, and enthusiastic release notes by pulling live data from GitHub and synthesizing every PR into a cohesive narrative.
Workflow
1. Fetch Release Data
Run the bundled script to pull the release metadata and all linked PR details in one shot:
bash .forge/skills/write-release-notes/scripts/fetch-release-data.sh <version> [owner/repo]
<version>: The release tag (e.g.v1.32.0)[owner/repo]: Optional. Defaults to the current repo detected viagh repo view.
The script outputs two sections:
### RELEASE METADATA ###— tag name, publish date, release name, raw body### PR DETAILS ###— one JSON object per PR with:number,title,body,labels,author,mergedAt,url
2. Categorize Changes
Group PRs by their conventional commit prefix or label:
| Category | Prefixes / Labels |
|---|---|
| Features | feat, type: feature |
| Bug Fixes | fix, type: fix |
| Performance | perf |
| Refactors | refactor |
| Maintenance | chore, docs, ci, build, deps |
Dependency bumps (e.g. Dependabot PRs) go into Maintenance. Skip PRs with error: "not found".
3. Write the Release Notes
Produce a Markdown document with the following structure. Keep the tone informative and enthusiastic — explain what changed and why it matters, without resorting to marketing fluff.
# [Product Name] [Version] — [Descriptive Tagline]
> One-sentence summary of what this release focuses on.
## What's New
[2-4 sentence narrative covering the biggest features and fixes.
Describe what changed and what users can now do. Use active voice. Be factual but upbeat.]
## Highlights
### [Feature/Fix Category]
**[PR Title rephrased as a clear description of the change]**
[1-2 sentences expanding on the PR description. Explain what changed and what users can now do differently.
If the PR body has useful context, distill it. If empty, infer from the title.]
[Repeat for each significant PR — skip pure chores/dep bumps unless noteworthy]
## Bug Fixes & Reliability
[Bullet list of fixes, each with a brief impact statement]
## Under the Hood
[Brief paragraph or bullet list covering refactors, maintenance, and dep updates —
keep it light, acknowledge the work without boring the reader]
## Contributors
A huge thank you to everyone who made this release happen: [list @handles — exclude bots like @dependabot]
---
**Full changelog**: [GitHub Release link]
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 130 lines · 105 tokens per session scan A 91f2ef140471
write-release-notes is a skill published in the GitHub repository justrach/codegraff2 (24 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 105 tokens to every session and 1,328 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to write-release-notes, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…