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/cligit 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/cli)<a href="https://agentmods.dev/commands/xzawed/claude-grok-build-plugin/cli"><img src="https://agentmods.dev/badge/commands/xzawed/claude-grok-build-plugin/cli.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 | $0.00011 | $0.00234 |
| Opus 5 | $0.00005 | $0.00117 |
| Sonnet 5 | $0.00002 | $0.00047 |
| Haiku 4.5 | $0.00001 | $0.00023 |
Grade A, and why
cli 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 3d 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.
What it actually says
Parse the user's raw Grok arguments into a string array and call grok_cli with that as
args. This is the escape hatch for any Grok subcommand not covered by a dedicated
/grok:* command.
- If
statusisblocked, relay themessageverbatim — the command is a TUI/server/shell or interactive-login command that must be run in a real terminal. - Otherwise present
stdoutTail(andstderrTailon error) and note the reportedbilling(the configured mode, not an observed charge; the billing-safe env applies even to a raw-pprompt). - Passthrough runs are not recorded to delegation history and are not gated by the
pre-delegate auth hook (unlike
/grok:delegate|plan|verify). Billing stays safe, but for an auditable, provenance-tracked coding edit use/grok:delegateinstead of a raw-ppassthrough.
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.
- 3d ago First seen · 17 lines · 11 tokens per session scan A 8e4422a4bbb0
cli is a command published in the GitHub repository xzawed/claude-grok-build-plugin (1 stars, last pushed 10d ago), licensed MIT. It adds 11 tokens to every session and 234 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.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
init
Install the formatters this repository needs, with every command visible before it runs.
setup
Fetch Kobiton credentials from the authenticated MCP server and write them to /.kobiton/.credentials.
discuss
5-phase requirements-elicitation interview that produces an EARS-validated context/ .md.