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/xh/hoist-corenpx agentmods add skills/xh/hoist-core/xh-upgrade-notesWrote 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/xh/hoist-core/xh-upgrade-notes)<a href="https://agentmods.dev/skills/xh/hoist-core/xh-upgrade-notes"><img src="https://agentmods.dev/badge/skills/xh/hoist-core/xh-upgrade-notes/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/xh/hoist-core/xh-upgrade-notes"><img src="https://agentmods.dev/badge/skills/xh/hoist-core/xh-upgrade-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00106 | $0.03163 |
| Opus 5 | $0.00053 | $0.01581 |
| Sonnet 5 | $0.00021 | $0.00633 |
| Haiku 4.5 | $0.00011 | $0.00316 |
Grade A, and why
xh-upgrade-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 9d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upgrade Notes Skill
Verify, finalize, and write upgrade documentation for a major Hoist Core release. This skill produces two artifacts: a CHANGELOG entry and a detailed upgrade-notes document.
Version: $ARGUMENTS
Phase 0: Setup
- Determine the target version. If
$ARGUMENTSprovides a version, normalize tovNNshort form andNN.x.xfull form. If no argument is provided, read the topmost entry inCHANGELOG.md— if it's a-SNAPSHOTentry, use that version as the target. - Identify the prior major version by reading
CHANGELOG.mdto find the entry immediately before the target version (e.g. if target is v38, prior is v37.x). - Determine the git range for diffing. If the prior version has been tagged, use the tag
range
v{prior}..HEAD(orv{prior}..v{target}if the target is also tagged). List available tags withgit tag -l 'v*'to find exact tag names. If no prior tag exists, usegit log --onelineto identify the boundary commit. - Read template.md for the upgrade notes document template.
- Read
docs/changelog-format.mdfor CHANGELOG entry conventions.
Phase 1: Research
Gather all information needed to write accurate documentation.
1a. Git History Analysis
- Run
git log --oneline {range}to see all commits in the release. - Run
git diff --stat {range}to understand scope of changes. - Read the existing CHANGELOG SNAPSHOT entry to understand what's already documented.
1b. Targeted Source Analysis
Let the git diff guide what to read — do not blindly read a fixed list of source files. Focus on:
build.gradle— always check for dependency version changes- Files touched by commits that aren't already reflected in the CHANGELOG
- Source files for any breaking changes (to verify accuracy of class/method/prop names)
The goal is to verify CHANGELOG accuracy and find gaps, not to read the entire codebase.
1c. Sample App Upgrade Analysis
What ships with it
1 file 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.
- 9d ago First seen · 262 lines · 106 tokens per session scan A 93adc02a2c03
xh-upgrade-notes is a skill published in the GitHub repository xh/hoist-core (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 106 tokens to every session and 3,163 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 2026-08-30.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.
updater_guide
Guidance for checking for and installing Row-Bot updates.