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 kai-wedekind/claude-code-grok-bridge/plugin install grok-buildWrote 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/kai-wedekind/claude-code-grok-bridge/show)<a href="https://agentmods.dev/commands/kai-wedekind/claude-code-grok-bridge/show"><img src="https://agentmods.dev/badge/commands/kai-wedekind/claude-code-grok-bridge/show.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 | $0.00015 | $0.00368 |
| Opus 5 | $0.00008 | $0.00184 |
| Sonnet 5 | $0.00003 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
show scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
!node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-bridge.mjs" show "$ARGUMENTS"
Behaviour:
- Without a run id, shows the latest finished run for the current Claude session.
- With an explicit run id, looks up that id in the workspace (not session-filtered).
--waitrequires a run id and polls until the run is finished or the wait deadline expires (default 240000 ms; override with--timeout-ms). Wait timeout exits 3 and prints status rather than a result payload.- Process exit reflects the stored run status (0 on successful completion, non-zero on failed/cancelled).
- When Grok fanned out to its own subagents, a
Subagents:block lists each strand with its type, status, output size and tool-call count, and warns when any strand produced nothing — a run whose answer rests on two of six strands cost the same as one where all six delivered.--strandsprints every strand's full deliverable instead of just the summary.
Present the full command output to the user. Do not summarize or condense it. Preserve all details including:
- Run ID and status
- The complete result payload, including verdict, summary, findings, details, artifacts, and next steps
- File paths and line numbers exactly as reported
- Any error messages or parse errors
- Follow-up commands such as
/grok-build:runs <id>and/grok-build:review
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 · 23 lines · 15 tokens per session scan A 0ecd327163c9
show is a command published in the GitHub repository kai-wedekind/claude-code-grok-bridge (2 stars, last pushed 16d ago), licensed Apache-2.0. It adds 15 tokens to every session and 368 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
delegate-claude
Delegate to local Claude Code (Grok background task; live tools in task log).
delegate-codex
Delegate to local Codex CLI (Grok background task; live tools in task log).
login
Sign in to Grok Build CLI using the default install path.
delegate
Delegate a coding task to Grok.
memory
Manage Grok cross-session memory.
review
Review Grok output (diff gate — never auto-commit).