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 agentmods add commands/xzawed/claude-grok-build-plugin/updategit clone --depth 1 https://github.com/xzawed/claude-grok-build-pluginWrote 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/commands/xzawed/claude-grok-build-plugin/update)<a href="https://agentmods.dev/commands/xzawed/claude-grok-build-plugin/update"><img src="https://agentmods.dev/badge/commands/xzawed/claude-grok-build-plugin/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 | $0.00010 | $0.00270 |
| Opus 5 | $0.00005 | $0.00135 |
| Sonnet 5 | $0.00002 | $0.00054 |
| Haiku 4.5 | $0.00001 | $0.00027 |
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 today.
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.
What it actually says
⚠️ A bare grok update installs. Checking is the opt-in --check. So "is there a new
version?" must not become a binary replacement.
Call grok_cli with:
["update","--check","--json"]— the default for any question about versions. ReturnscurrentVersion/latestVersion/updateAvailableand changes nothing.["update"]— downloads and installs. Only when the user explicitly asked to update.["update","--version","<v>"]to pin a version,--alpha/--stableto switch channel,--force-reinstallto re-download the current version.
When you do install, pass a larger timeout_ms (the default is 60 s and a slow download is
SIGKILLed mid-install, surfacing as status: "timeout" after the binary was already being
replaced). Note the CLI also updates itself outside this command — a version measured today
is not a version guaranteed tomorrow.
Present stdoutTail; on error show stderrTail. If status is blocked, relay the
message.
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.
- today Changed · +15 lines · +3 tokens per session 0710a9cefc8a
- 4d ago First seen · 8 lines · 7 tokens per session scan A 20efc661589b
update is a command published in the GitHub repository xzawed/claude-grok-build-plugin (1 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 270 once invoked, about $0.0001 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 commands, from other repositories
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
techdebt
Find and report technical debt in the codebase.
merge
Finish a PR properly: every check green, every review addressed — human and bot — then merge and clean up.
pr
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.
spec
Spec-first design: a gap-closing interview that produces a complete spec, with a quality controller that blocks until every section is answered and every question resolved.
plan
Turn an approved spec into an implementation plan an engineer with zero context could execute — with a quality controller that blocks placeholders and hollow tasks.