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/detach)<a href="https://agentmods.dev/skills/jebel-quant/rhiza-claude/detach"><img src="https://agentmods.dev/badge/skills/jebel-quant/rhiza-claude/detach/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/jebel-quant/rhiza-claude/detach"><img src="https://agentmods.dev/badge/skills/jebel-quant/rhiza-claude/detach.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00045 | $0.00855 |
| Opus 5 | $0.00023 | $0.00428 |
| Sonnet 5 | $0.00009 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
detach 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /detach in the current working directory's repo.
This command is a thin wrapper around the bundled plugin/scripts/detach.py. All
the deletion logic lives in that script — a deterministic, stdlib-only Python
program that reads .rhiza/template.lock directly (no rhiza CLI, no PyYAML
required). Do not re-implement it or delete files yourself; run the script.
⚠️ This is destructive. It permanently deletes the files rhiza synced into the
repo, removes the directories they leave empty, and deletes .rhiza/template.lock
so the repo is no longer rhiza-managed. Files you added yourself are untouched.
This detaches a repo, not the plugin. It is the inverse of the sync, not of the
installation — the rhiza plugin stays installed and every other repo stays managed. A
user who wants the plugin itself gone from Claude Code wants /plugin, not this. If
that is what they appear to be asking for, say so rather than deleting their files.
Argument (optional): $ARGUMENTS — a path to the repo root to clean; default is
the current directory.
1. Confirm intent first
Because this deletes files, confirm with the user before running unless they
have already clearly asked to proceed (e.g. said "yes, detach" or passed
--force). Recommend they have a clean git tree / committed work first, so the
deletion is easy to review and revert.
2. Run the script
Invoke it with the plugin-root path (it ships inside this plugin, so
${CLAUDE_PLUGIN_ROOT} resolves at runtime — keep the quotes):
uv run --python 3.12 --no-project python "${CLAUDE_PLUGIN_ROOT}/scripts/detach.py" $ARGUMENTS --force
- Pass
$ARGUMENTSthrough as the optional target path. If it's empty, just omit it. - The script normally prompts
[y/N]for confirmation. When run non-interactively (as here, with no TTY to answer) an unanswered prompt is treated as "no" and it cancels — so pass--force(equivalently-y) only after the user has confirmed in step 1, to carry out the deletion they approved.
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 · 62 lines · 45 tokens per session scan A 6c4ab5707f3a
detach is a skill published in the GitHub repository Jebel-Quant/rhiza-claude (4 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 855 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
detect-task
Internal skill for commands. Detect the active task (any tracker adapter) from the task-state file / git branch name. Do not trigger on user conversation - only when commands need task detection.
loop-bb-pr
A command that prepares a repeating check for a Bitbucket pull request. A pull request is a request to review and merge code changes into a project.
take-task
A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.
session-boundary
Internal skill for commands. Resolve and VALIDATE this branch's session boundary - the ref a session's commit range is measured from - and report how much it can be trusted. Do not trigger on user conversation; only when a command needs the session range.
commit
A guided process for committing code changes to Git. It checks the working tree, follows a conventional commit format, links a task when available, reviews the changes, and asks for approval.
release
Prepare a version release — bump version files, commit, and tag. Just run /release with no arguments.