An uninstall command for the model-guard status line, a small display shown in the Claude Code interface. It can restore the status line that was used before model-guard and optionally remove its files.

Use it when removing model-guard from Claude Code, either together with its script and configuration or while keeping those files.

It removes the status line without losing a previously configured one and creates a backup before changing settings.

remove — Skill for Claude Code by ventusff/claude-model-guard

Install

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.

Any agent

npx skills add ventusff/claude-model-guard --skill remove

Clone the repo

git clone --depth 1 https://github.com/ventusff/claude-model-guard

Made for: Claude Code.

Or install model-guard, the plugin that ships this one along with the rest of its 3 skills, 7 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ventusff/claude-model-guard/remove/github.svg)](https://agentmods.dev/skills/ventusff/claude-model-guard/remove)

Your own site

<a href="https://agentmods.dev/skills/ventusff/claude-model-guard/remove"><img src="https://agentmods.dev/badge/skills/ventusff/claude-model-guard/remove/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ventusff/claude-model-guard/remove"><img src="https://agentmods.dev/badge/skills/ventusff/claude-model-guard/remove.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 603 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00040	$0.00603
Opus 5.5	$0.00016	$0.00241
Sonnet 5.5	$0.00008	$0.00121
Haiku 4.5	$0.00004	$0.00060

Measured 2mo ago against content hash 777f3f43a9e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

remove scanned grade D with 2 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

description: Cleanly uninstall the model-guard statusline — unregisters statusLine from ~/.claude/settings.json (restoring any previously saved statusline), and optionally deletes the installed scripts and config.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

b) If deleting files: `rm -rf ~/.claude/model-guard; rm -f ~/.claude/model-guard.sh ~/.claude/model-guard.conf`

skills/remove/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

model-guard: uninstall

You are removing the model-guard statusline for this user. Keep the final report short.

1. Inspect (one Bash call)

Read ~/.claude/settings.json → .statusLine.command.
Read ~/.claude/model-guard.conf if present → note PREV_STATUSLINE_B64.
If the current statusLine is NOT model-guard (command doesn't contain model-guard), say so — only offer file cleanup (step 3b), don't touch settings.

2. Ask (ONE AskUserQuestion call)

Header "Cleanup": "Unregister + delete files (Recommended)" / "Unregister only (keep scripts & config)".

3. Execute

Backup first: cp ~/.claude/settings.json ~/.claude/settings.json.bak-model-guard-$(date +%Y%m%d-%H%M%S)

a) Unregister — restore the pre-model-guard statusline if one was saved:

If the conf has PREV_STATUSLINE_B64:

jq --argjson sl "$(sed -n 's/^PREV_STATUSLINE_B64=//p' ~/.claude/model-guard.conf | base64 -d)" \
  '.statusLine=$sl' ~/.claude/settings.json > ~/.claude/settings.json.tmp \
  && mv ~/.claude/settings.json.tmp ~/.claude/settings.json

Otherwise: jq 'del(.statusLine)' ... (same tmp+mv pattern).
Validate the result parses: jq . ~/.claude/settings.json >/dev/null.

b) If deleting files: rm -rf ~/.claude/model-guard; rm -f ~/.claude/model-guard.sh ~/.claude/model-guard.conf (the flat model-guard.sh exists only on installs made before the directory layout) and the per-session recovery state: rm -rf "${XDG_RUNTIME_DIR:-/tmp}/model-guard". If ~/.config/kitty/kitty.conf carries the two remote-control lines that setup added (allow_remote_control socket-only, listen_on unix:@kitty), mention them — they are harmless, the user decides whether to keep them.

4. Report (short)

StatusLine unregistered (and previous statusline restored, if there was one); a timestamped settings backup was kept.
The plugin itself can be uninstalled with /plugin → Manage plugins, or claude plugin uninstall model-guard@claude-model-guard.

Read the full file on GitHub · 51 lines

Changes

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.

2mo ago Changed · +1 lines 777f3f43a9e4
2mo ago Changed · +4 lines scan B → D b6342bfc8d94
2mo ago First seen · 46 lines · 40 tokens per session scan B a1243f2c5283

Subscribe to this mod's changes

remove is a skill published in the GitHub repository ventusff/claude-model-guard (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 603 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code claude claude-code-plugin plugin statusline

remove next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
removeventusff/claude-model-guard	Skill	2	1mo ago	MIT	D	40	Claude Code
codex-setupWaterTian/cc-hud	Skill	9	4d ago	MIT	A	43	Claude Code, Codex
prumputun/cc-thingz	Skill	494	6d ago	MIT	A	51	Claude Code
backlogumputun/cc-thingz	Skill	494	6d ago	MIT	A	96	Claude Code
clarifyumputun/cc-thingz	Skill	494	6d ago	MIT	A	91	Claude Code
writing-styleumputun/cc-thingz	Skill	494	6d ago	MIT	A	52	Claude Code
root-cause-investigatorumputun/cc-thingz	Skill	494	6d ago	MIT	A	53	Claude Code

remove