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 bearlike/Grove --skill reinstalling-grovegit clone --depth 1 https://github.com/bearlike/GroveWrote 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/bearlike/grove/reinstalling-grove)<a href="https://agentmods.dev/skills/bearlike/grove/reinstalling-grove"><img src="https://agentmods.dev/badge/skills/bearlike/grove/reinstalling-grove.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 | $0.00160 | $0.04063 |
| Opus 5 | $0.00080 | $0.02031 |
| Sonnet 5 | $0.00032 | $0.00813 |
| Haiku 4.5 | $0.00016 | $0.00406 |
Grade D, and why
reinstalling-grove scanned grade D with 3 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
> Grove entrypoint that was once run as root** — CPython wrote uid-0 bytecode Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s http://127.0.0.1:7421/openapi.json | python3 -c \ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
for i in $(seq 1 15); do c=$(curl -s -o /dev/null -w "%{http_code}" --max-time 2 \ How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reinstalling & updating Grove
Grove ships as one Python package whose
surfaces update through different mechanisms — three core ones (CLI/TUI,
daemon, webapp) plus the opt-in grove-mcp server, whose
staleness rules differ by transport. Most "I updated but
still see the old version" reports come from updating one surface and forgetting
another, or from a process/browser still holding the old code. This skill makes
the update deterministic and gives you a decision tree for the stale-UI case.
The golden rule, and the thing to repeat to the user: new code on disk does not change anything already running. A live process loaded its modules at startup; a long-lived service keeps running the old build until restarted; a browser serves a cached page. Updating Grove is therefore never "just pull" — it is pull, then refresh each surface that needs it.
1. The surfaces and how each updates
| Surface | What it is | How it picks up new code |
|---|---|---|
| Package — CLI + TUI | the grove command and its Textual UI |
a fresh grove invocation (editable install) OR a uv tool install --reinstall when deps changed |
| Daemon | grove daemon serve, the loopback HTTP + tmux service (default 127.0.0.1:7421) |
service restart (it is long-lived) |
| Webapp | the Next.js dashboard (default :3000) |
rebuild .next THEN restart the webapp service |
| MCP server (opt-in) | grove-mcp (MCP client → grove-mcp → daemon REST → core), in one of two transports |
depends entirely on the transport — see below |
The MCP server is the one surface whose answer depends on how it is running, and getting this wrong is silent rather than loud.
- stdio — not a long-lived process you own. The MCP client spawns a fresh
grove-mcpper connection, so an editable install's new code is live on its next launch and there is nothing to restart. - networked (
--transport streamable-http) — a long-lived server exactly like the daemon, usually agrove-mcp.serviceunit. It must be restarted. A reinstall swaps the tool venv its entrypoint lives in, but a running process keeps the modules it already imported, so it will happily keep serving the previous build.
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 · 288 lines · 160 tokens per session scan D 93b235a6a687
reinstalling-grove is a skill published in the GitHub repository bearlike/Grove (2 stars, last pushed 17d ago), licensed MIT. It adds 160 tokens to every session and 4,063 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
content-planner
GSC-driven content calendar. Pulls real Search Console data, finds the highest click-potential opportunities (striking-distance queries at positions 5-20, unanswered query intent, related-keyword expansions), and produces a dated, prioritized content calendar — ready to hand to /content-writer. Use when the user asks…
meta-tags-optimizer
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…
setup-cms
Connect a CMS to notfair SEO tools. Guides users through configuring WordPress, Strapi, Contentful, or Ghost — tests the connection, and writes credentials to .env.local. Once set up, seo-analysis automatically cross- references CMS content against Google Search Console data. Use whenever the user says "connect my…
broken-link-checker
Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing. Use this when the user asks to "check for broken links", "find 404s", "audit my links", or "is my site healthy".
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
google-ads-copy
Generate and A/B test Google Ads copy. Use when asked to write ad copy, headlines, descriptions, create ad variants, test ad messaging, improve CTR, or generate RSA (Responsive Search Ad) components. Trigger on "ad copy", "write ads", "headlines", "descriptions", "RSA", "responsive search ad", "ad text", "ad…