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/greenpolo/cc-multi-cli-plugin/executegit clone --depth 1 https://github.com/greenpolo/cc-multi-cli-pluginWhat 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 | $0.00012 | $0.00552 |
| Opus 5 | $0.00006 | $0.00276 |
| Sonnet 5 | $0.00002 | $0.00110 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade A, and why
execute 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 yesterday.
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
Invoke the multi:codex-execute subagent via the Agent tool, forwarding the user's request as the prompt.
The subagent runs Codex in structured-execution mode — give it a concrete plan step, it implements it.
This is distinct from the official openai-codex plugin's /codex:rescue, which handles open-ended rescue. Use /codex:execute when you have a clear plan step; use /codex:rescue when Claude is stuck.
Raw user request: $ARGUMENTS
Execution:
- Plan-by-reference (preferred when applicable): if a plan file is in conversation context (Plan mode
Plan File Infoblock, a path like~/.claude/plans/*.md, or a plan you authored this session), pass--plan <path>instead of paraphrasing. The subagent translates--planto--prompt-fileand Codex reads the file's bytes directly. See themulti-plan-handoffskill for full detection rules. Trigger phrases like "execute it via codex", "delegate to codex", "send this plan to codex" all qualify. - For a small, clearly bounded step, invoke the subagent in the foreground (blocking).
- For a long-running or high-effort step (or
--until-done), invoke the subagent with theAgenttool'srun_in_background: true: the subagent runs Codex to completion in the foreground, so the harness wakes you with a<task-notification>when it finishes, fails, or the inactivity watchdog kills a hang — instead of stalling silently. Do NOT add the companion's--backgroundflag for this (it detaches a worker the harness can't see); keep--backgroundas an explicit fire-and-forget opt-in polled via/multi:status. - Preserve
--modeland--effortflags for the forwarded command — the subagent reads them. - If the user passes
--resume, the subagent will continue the latest Codex execute thread for this repo. - If the request includes no prompt text AND no plan file in context, ask what Codex should implement before proceeding.
Return Codex's output 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.
- yesterday First seen · 26 lines · 12 tokens per session scan A 6d0fe7387f21
execute is a command published in the GitHub repository greenpolo/cc-multi-cli-plugin (89 stars, last pushed 16d ago), licensed Apache-2.0. It adds 12 tokens to every session and 552 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
delegate
Delegate to Cursor, Composer, or cursor-agent via cursor-delegate-mcp (see delegate skill).
icpg-bootstrap
Infer ReasonNodes from existing git commit history. One-time setup for existing codebases.
version
Display current guide and Claude Code versions.
go-review
Go code review for idiomatic patterns.
release-harn
Run the tag-first Harn release workflow.
esp-harden
Harden and inspect ESP32 firmware for field failures, crashes, memory, and security.