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 skills add Kevin-Liu-01/Agent-Machines --skill hotfix-previewgit clone --depth 1 https://github.com/Kevin-Liu-01/Agent-MachinesWrote 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/kevin-liu-01/agent-machines/hotfix-preview)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/hotfix-preview"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/hotfix-preview/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/kevin-liu-01/agent-machines/hotfix-preview"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/hotfix-preview.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 | $0.00046 | $0.00385 |
| Opus 5 | $0.00023 | $0.00192 |
| Sonnet 5 | $0.00009 | $0.00077 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
hotfix-preview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
When to use
A fix is on dev and needs to reach preview (and then prod) immediately.
The full /promote flow creates a changelog PR that needs review and merge.
This skill skips the PR and cherry-picks directly.
Rules
- The commit must already exist on
dev. Do not cherry-pick unmerged work. - Cherry-pick creates a new SHA on
preview. The original SHA stays ondev. Both branches contain the same diff; history diverges by one merge-base commit. This is fine —/promotereconciles them on the next full promotion. - Never force-push
previewordev.
Task
set -euo pipefail
REMOTE="${REMOTE:-upstream}"
SHA="${1:-$(git rev-parse "$REMOTE/dev")}"
# Validate the commit exists on dev
if ! git merge-base --is-ancestor "$SHA" "$REMOTE/dev"; then
echo "error: $SHA is not on $REMOTE/dev" >&2
exit 1
fi
# Cherry-pick onto preview
git fetch "$REMOTE" preview
git switch preview
git pull --ff-only "$REMOTE" preview
git cherry-pick "$SHA"
git push "$REMOTE" preview
# Show result
echo ""
echo "Cherry-picked $(git rev-parse --short "$SHA") onto preview as $(git log -1 --format='%h') — $(git log -1 --format='%s')"
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 · 46 lines · 46 tokens per session scan A 8e2fdbbb4ac3
hotfix-preview is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 385 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
release-and-publish
Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
coding-worktree-recovery
Use this skill when coding-agent work is interrupted, an agent exits without a clean commit, multiple controllers target the same checkout, or the checkout produces inconsistent file/Git behavior.
fluent-brownfield-migration
This skill should be used when the user asks to "convert this app to fluent", "migrate a scoped app to source control", "modernize this servicenow app", "bring an existing app into git", "transform to fluent", or mentions "brownfield" migration of an existing ServiceNow scoped application to the ServiceNow SDK /…
update-set-workflow
Manage ServiceNow update sets — create named sets before any development, ensure autoswitch tracks API changes under the OAuth service account, complete on done, and export for promotion. Mandatory for all change-producing work.
bob-export
Create a Hacker Bob post-release improvement bundle for the currently installed Bob version.