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/arthurkatcher/grok-delegate/delegate-codexgit clone --depth 1 https://github.com/arthurkatcher/grok-delegateWhat 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 | $0.00018 | $0.00528 |
| Opus 5 | $0.00009 | $0.00264 |
| Sonnet 5 | $0.00004 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
delegate-codex 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 2d 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
Delegate to local OpenAI Codex CLI. Models/efforts from live codex debug models (GPT-5.6 Sol/Terra/Luna when CLI ≥ 0.144).
Launch (required)
Use exactly one run_terminal_command with background: true and timeout: 0 (or a very high timeout) so the host does not SIGTERM the companion after ~20s.
Flags before free text; use -- before focus. Prefer --payload-file for messy paste. Prefer --cwd at a real project/repo (not $HOME).
node "${GROK_PLUGIN_ROOT}/scripts/delegate-companion.mjs" codex --wait --model gpt-5.6-sol --effort ultra --sandbox read-only -- review -- "focus text"
- Expand the Grok task for live tools.
- Cancel the Grok task → stops Codex process tree.
- Do not poll status into chat.
If cwd is not a git work tree, the companion auto-passes --skip-git-repo-check so Codex does not refuse $HOME/non-repo dirs on first launch.
Sandbox
Action soft default (if --sandbox omitted) |
|---|
overview / review / adversarial → read-only |
rescue → workspace-write |
User can always pass --sandbox … or --yolo. --read-only rejects write sandboxes.
Auth / preflight
codex login or CODEX_API_KEY. Setup warns if CLI < 0.144 for GPT-5.6.
Every action (setup, overview, review, adversarial, rescue) runs the same readiness check first: Codex binary on PATH + login/API key. If not ready, the companion does not spawn Codex — it prints the setup-style next steps and exits non-zero.
Raw arguments:
$ARGUMENTS
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.
- 2d ago First seen · 43 lines · 18 tokens per session scan A 8da1cc0cf572
delegate-codex is a command published in the GitHub repository arthurkatcher/grok-delegate (13 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 528 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 2026-08-30.
Other commands, from other repositories
trellis-continue
Resume work on the current task — pick up at the right phase/step in .trellis/workflow.md.
continue
Resume work on the current task — pick up at the right phase/step in .trellis/workflow.md.
finish-work
Wrap up the current session: archive the active task (and any other completed-but-unarchived tasks the user wants to clean up) and record the session journal. Code commits are NOT done here — those happen in workflow Phase 3.4 before you invoke this command.
trellis-finish-work
Wrap up the current session: archive the active task (and any other completed-but-unarchived tasks the user wants to clean up) and record the session journal. Code commits are NOT done here — those happen in workflow Phase 3.4 before you invoke this command.
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
agentlas-cloud
Staff a task only from the signed-in owner's Agent Cloud agents.