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 dcb/homeassistant-claude-kit --skill releasegit clone --depth 1 https://github.com/dcb/homeassistant-claude-kitWrote 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/dcb/homeassistant-claude-kit/release)<a href="https://agentmods.dev/skills/dcb/homeassistant-claude-kit/release"><img src="https://agentmods.dev/badge/skills/dcb/homeassistant-claude-kit/release/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/dcb/homeassistant-claude-kit/release"><img src="https://agentmods.dev/badge/skills/dcb/homeassistant-claude-kit/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 149 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00116 | $0.03371 |
| Opus 5.5 | $0.00046 | $0.01348 |
| Sonnet 5.5 | $0.00023 | $0.00674 |
| Haiku 4.5 | $0.00012 | $0.00337 |
Grade A, and why
release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release the Kit
This skill is the producer half of kit versioning. It reads ONLY the kit's own git
history and writes the version artifacts — the git tag, .kit-version, kit-changelog.yaml,
CHANGELOG.md, and dashboard/package.json — in one commit so version and content always
travel together. It is idempotent per version: re-running it on a version that is already
released, tagged, and pushed is a no-op at every step (append-only changelog, pre-existing-tag
guard, idempotent GitHub release). The changelog's detect/apply prose is authored
generically and is never executed.
See references/changelog-schema.md for the full record schema, the intent contract, the
deterministic commit→type mapping, and the rendering rules.
Step 0: Prerequisites
Run each check; branch on the sentinel it prints.
# Clean working tree (untracked files are allowed; tracked modifications are not)
git diff --quiet && git diff --cached --quiet && echo "TREE_OK" || echo "TREE_DIRTY"
# On the default branch
def=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@')
[ -z "$def" ] && def=main
[ "$(git branch --show-current)" = "$def" ] && echo "BRANCH_OK" || echo "BRANCH_WRONG"
# A baseline tag exists and is >= v0.1.0
git fetch --tags --quiet 2>/dev/null
last=$(git tag --list 'v*' --sort=-v:refname | head -1)
[ -n "$last" ] && echo "LAST_TAG=$last" || echo "TAGS_MISSING"
# Signing capability (decides -s vs -a in Step 7)
if [ -n "$(git config --get user.signingkey)" ] && git tag -s __sigprobe__ -m x >/dev/null 2>&1; then
git tag -d __sigprobe__ >/dev/null 2>&1; echo "SIGN_OK"
else
git tag -d __sigprobe__ >/dev/null 2>&1; echo "SIGN_NONE"
fi
# GitHub CLI auth (for the release in Step 8)
gh auth status >/dev/null 2>&1 && echo "GH_OK" || echo "GH_NONE"
- TREE_DIRTY → stop. Tell the user to commit or stash; a release commits a curated set, never accidental WIP.
- BRANCH_WRONG → stop. Releases are cut from the default branch only.
- TAGS_MISSING → stop. The baseline
v0.1.0tag must exist first (it is created once, during the versioning foundation). Do not invent one. - SIGN_NONE → continue, but downgrade the Step-7 tag from
git tag -stogit tag -aand log: "no usable signing key — creating an annotated (unsigned) tag." Never abort for this. - GH_NONE → continue; in Step 8 skip
gh release createand print the exact command for the user to run later.
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.
- 1mo ago First seen · 198 lines · 116 tokens per session scan A 40b2ea9895d1
release is a skill published in the GitHub repository dcb/homeassistant-claude-kit (125 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 3,371 once invoked, about $0.0005 per session on Opus 5.5. 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.
release
Fully automate a release with version-bump and childhood.
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.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.
updater_guide
Guidance for checking for and installing Row-Bot updates.