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/jayrha/agentskills/release-notes-writernpx skills add JayRHa/AgentSkills --skill release-notes-writergit clone --depth 1 https://github.com/JayRHa/AgentSkillsWhat 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 | $0.00103 | $0.01568 |
| Opus 5 | $0.00051 | $0.00784 |
| Sonnet 5 | $0.00021 | $0.00314 |
| Haiku 4.5 | $0.00010 | $0.00157 |
Grade A, and why
release-notes-writer 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Notes Writer
Overview
This skill turns raw engineering output — merged PRs, commit messages, issue references, and changelog fragments — into release notes that a real user can read and act on. It enforces a consistent structure, a user-facing voice (benefit first, not implementation detail), correct categorization (especially surfacing breaking changes), and an upgrade/migration section when needed.
Keywords: release notes, changelog, CHANGELOG.md, version bump, breaking changes, migration guide, semver, what's new, release announcement, GitHub release, conventional commits.
Use this skill whenever the user has a set of changes (any of: PR titles, git log output, conventional-commit messages, a list of Jira/GitHub issues, or an existing draft) and wants them shaped into publishable notes.
When NOT to use
- A single trivial change with no user impact — just describe it.
- Internal-only commit summaries with no audience — use a plain commit log.
- Writing the code itself — this skill writes the notes, not the changes.
Inputs to gather first
Before drafting, confirm or infer:
- Version & date — e.g.
v2.4.0,2026-06-08. Infer semver bump from the changes (see references/categorization.md). - Audience — end users, API consumers/developers, or internal team. This changes vocabulary and depth.
- Source material — PR list, commit log, or changelog fragments.
- Format target — Markdown
CHANGELOG.md(Keep a Changelog style), a GitHub Release body, a blog-style announcement, or in-app "What's New". If any are missing, ask once, concisely. Do not block on perfect input — infer sensible defaults and state your assumptions.
Workflow
- Collect changes. If given a git range, run the helper:
python scripts/parse_commits.py --range v2.3.0..HEAD(or pipegit log). It parses conventional commits, groups them, and flags!/BREAKING CHANGEas breaking. Review its output — never publish it raw. - Filter noise. Drop chore/ci/build/refactor/test/docs commits that have zero user impact. Merge duplicates and revert+reland pairs. Keep anything a user can see, feel, or must react to.
- Categorize every surviving change into exactly one of: Breaking Changes, Features (✨ new), Improvements (⚡ enhancements/perf/UX), Bug Fixes (🐛), Deprecations, Security. Use the decision table in references/categorization.md.
- Rewrite each line into the user-facing voice: lead with the benefit/outcome, present tense, active voice, no internal jargon, no PR/branch names in prose. Append issue/PR references in parentheses. See the rewrite patterns below and references/style-guide.md.
- Determine the version bump from the highest-severity category present (breaking → major, feature → minor, fix-only → patch). State it.
- Write the Breaking Changes + Migration section first if any exist — this is the highest-value content. Give before/after and concrete migration steps.
- Assemble using templates/changelog-entry.md (for CHANGELOG.md) or templates/github-release.md (for a release body). Add a one-line highlight summary at the top.
- Self-check against references/checklist.md. Verify ordering (Breaking → Security → Features → Improvements → Fixes → Deprecations), no empty sections, every breaking change has migration guidance, and links resolve.
What ships with it
7 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.
- 2d ago First seen · 82 lines · 103 tokens per session scan A 33bdc3c8ff85
release-notes-writer is a skill published in the GitHub repository JayRHa/AgentSkills (4 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,568 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
reverse-engineering-tools
Guide for reverse engineering protected games and anti-cheat components across user mode, kernel mode, and hypervisor-aware environments. Use this skill when analyzing drivers, IOCTL protocols, callback registration, injected-code artifacts, integrity checks, protected binaries, or debugging security-sensitive game…
unity-agent-workflows
Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first…
interpreting-mod-author-instructions
Use when deciding how to correctly download/install a Bethesda mod per the author's instructions — triggers "how do I install", "FOMOD choices", "which file to download", "author说明", "install instructions", "which variant", "按作者说明安装", "这个mod怎么装". NOT for deciding whether to include the mod (use evaluating-bgs-mods)…
using-bgs-archive
Use when the user wants to inspect, list, extract, unpack, or repack Bethesda BA2/BSA archives; determine archive format/version/compression; or build archive assets for an MO2 overlay. Triggers - "unpack BA2", "extract BSA", "pack archive", "inspect archive", "bgs-archive".
orchestrate
Pipeline orchestration: dispatch the highest-priority ready tasks/work units to agents, manage capacity, and coordinate the Todo to Done flow. Invoked as /agiflow:orchestrate. Uses listtasks, listactivetasksbyorg, listmembers, updatetask, getworkunitprogress.
design-director
Используй только внутри активного Codex Project Autopilot-проекта, когда уже выбрана проектная фаза и нужен design direction по плану автопилота.