Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Jebel-Quant/rhiza-claude/plugin install rhizaWrote 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/jebel-quant/rhiza-claude/update)<a href="https://agentmods.dev/skills/jebel-quant/rhiza-claude/update"><img src="https://agentmods.dev/badge/skills/jebel-quant/rhiza-claude/update.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00044 | $0.02833 |
| Opus 5 | $0.00022 | $0.01417 |
| Sonnet 5 | $0.00009 | $0.00567 |
| Haiku 4.5 | $0.00004 | $0.00283 |
Grade A, and why
update 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 7d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /update in the current working directory's repo. Goal: bump the
template ref, apply the sync, and open a PR with nothing but template-owned
files in it.
Only files that come from the template repository may be touched. The sync
records exactly which paths it materialized in .rhiza/template.lock's files list,
and plugin/scripts/stage_synced.py (step 7) stages precisely that set — so the guarantee is
mechanical, not something this prose has to be trusted to honour. Never
git add --all and never fold in unrelated edits: no reformatting of the repo's own
source, no dependency changes, no test fixes. Anything outside the set stays in the
working tree and gets reported.
No gates, no scorecard, no issues. /update syncs; /quality scores. Don't run
make test/make lint/make fmt here — make fmt in particular would rewrite the
repo's own files and break the rule above. Point the user at /rhiza:quality in the
report instead.
Argument (optional): $ARGUMENTS — an explicit template version tag like v1.2.0.
If empty, use the template's latest release.
Work through these steps. Stop and report if a precondition fails.
1. Preconditions
uvfirst.Read${CLAUDE_PLUGIN_ROOT}/prompts/install-uv.mdand follow it before anything else (in a source checkout,plugin/prompts/install-uv.md). It's a one-line no-op whenuvis already present. The sync runs throughuv run --python 3.12, so ifuv --versionstill fails afterwards, stop — don't fall back to a systempython3, which on macOS is 3.9 and crashessync.pyondatetime.UTC. (prompts/*.mdare internal procedures, not slash commands — not in any directory Claude Code scans, so the user can't invoke them; reach them withRead.).rhiza/template.ymlmust exist. If not, stop: "Not a rhiza-managed repo (no .rhiza/template.yml)" — and point at/rhiza:init, which establishes that file.- The working tree must be clean (
git status --porcelain). If dirty, stop and show the dirty files; the sync refuses a dirty tree anyway (exit 2). - Record
ORIG_BRANCH(git branch --show-current) — step 8 returns to it — the default branchDEFAULT(gh repo view --json defaultBranchRef --jq .defaultBranchRef.name, elsegit remote show origin, elsemain), and the platform fromgit remote get-url origin(github.com→ GitHub/gh; a GitLab host → GitLab/glab).
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.
- 7d ago First seen · 179 lines · 44 tokens per session scan A 1e34f781a856
update is a skill published in the GitHub repository Jebel-Quant/rhiza-claude (4 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 2,833 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 2026-08-31.
Other skills, from other repositories
release
Prepare a version release — bump version files, commit, and tag. Just run /release with no arguments.
release-init
Detect project type and generate a tailored project-level /release skill. Run once per project to set up releasing.
watch-tag
Watch a GitHub repository for new tags using the gh-watch extension. Use when the user wants to be notified when a tag is created, when a release is cut, or when a tag that includes a specific commit appears (e.g. "tell me when my merge ships in a release").
release
Use when the user wants to publish a new release, says "release", "publish release", "cut a release", or "new version". Covers tag creation, CI-driven build, and troubleshooting.
gitlab-release
GitLab release operations. ALWAYS use this skill when user wants to: (1) list releases, (2) view release details, (3) create new releases, (4) upload assets, (5) delete releases.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.