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/lovelaceloom/grok-plugin-cc/worktreegit clone --depth 1 https://github.com/LovelaceLoom/grok-plugin-ccWhat 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 | $0.00016 | $0.00253 |
| Opus 5 | $0.00008 | $0.00127 |
| Sonnet 5 | $0.00003 | $0.00051 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
worktree 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
Wrap grok worktree. Subcommands match the underlying CLI:
/grok:worktreeor/grok:worktree list— list active Grok-managed worktrees/grok:worktree gc— garbage-collect stale worktrees/grok:worktree rm <name>— remove a specific worktree- Pass
--jsonfor a machine-readable dump.
Worktrees pair with the --worktree [<name>] flag on /grok:rescue,
/grok:research, etc. — those start a session inside a fresh git worktree
so Grok can edit safely without touching the main checkout.
Raw user input:
$ARGUMENTS
Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" worktree "$ARGUMENTS"
Output rules:
- Return the companion's stdout verbatim.
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 · 30 lines · 16 tokens per session scan A a9794b8771d2
worktree is a command published in the GitHub repository LovelaceLoom/grok-plugin-cc (5 stars, last pushed 25d ago), licensed Apache-2.0. It adds 16 tokens to every session and 253 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
test-tools
Test MCP NixOS Tools (project).
spec-audit
Review — attack the SPEC before any code is written.
spec
Think — write the lean SPEC that the build will be measured against.
implement
Do — execute the SPEC in a fresh context, validating each step.
project
Think — plan the work and write a lean SPEC before building.
qa
Dispatch a verifiable browser task to the qa-tester subagent. Use for regression checks, smoke tests, and any task with a clean pass/fail outcome. Supports an EXHAUSTIVE mode that verifies every control behind an honesty gate.