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/agents365-ai/pi-plugin-cc/rescuegit clone --depth 1 https://github.com/Agents365-ai/pi-plugin-ccWrote 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/agents365-ai/pi-plugin-cc/rescue)<a href="https://agentmods.dev/commands/agents365-ai/pi-plugin-cc/rescue"><img src="https://agentmods.dev/badge/commands/agents365-ai/pi-plugin-cc/rescue.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 | $0.00019 | $0.01057 |
| Opus 5 | $0.00010 | $0.00528 |
| Sonnet 5 | $0.00004 | $0.00211 |
| Haiku 4.5 | $0.00002 | $0.00106 |
Grade A, and why
rescue 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 5d 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.
This is a copy
80% identical to rescue — 46 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Invoke the pi:pi-companion-forwarder subagent via the Agent tool (subagent_type: "pi:pi-companion-forwarder"), forwarding the raw user request as the prompt.
pi:pi-companion-forwarder is a subagent, not a skill — do not call Skill(pi:pi-companion-forwarder) (no such skill) or Skill(pi:rescue) (that re-enters this command and hangs the session). The command runs inline so the Agent tool stays in scope; forked general-purpose subagents do not expose it.
The final user-visible response must be Pi's output verbatim.
Raw user request: $ARGUMENTS
Execution mode:
- If the request includes
--background, run thepi:pi-companion-forwardersubagent in the background. - If the request includes
--wait, run thepi:pi-companion-forwardersubagent in the foreground. - If neither flag is present, default to foreground.
--backgroundand--waitare execution flags for Claude Code. Do not forward them totask, and do not treat them as part of the natural-language task text.--model,--effort, and--out-fileare runtime-selection flags. Preserve them for the forwardedtaskcall, but do not treat them as part of the natural-language task text.--out-file <path>writes Pi's full output to<path>and returns only a short summary, keeping a large result out of the conversation to save tokens. Preserve it in the forwardedtaskcall; relay the short summary verbatim.- If the request includes
--resume, do not ask whether to continue. The user already chose. - If the request includes
--fresh, do not ask whether to continue. The user already chose. - Otherwise, before starting Pi, check for a resumable rescue session from this Claude session by running:
node "${CLAUDE_PLUGIN_ROOT}/scripts/pi-companion.mjs" task-resume-candidate --json
- If that helper reports
available: true, useAskUserQuestionexactly once to ask whether to continue the current Pi session or start a new one. - The two choices must be:
Continue current Pi sessionStart a new Pi session
- If the user is clearly giving a follow-up instruction such as "continue", "keep going", "resume", "apply the top fix", or "dig deeper", put
Continue current Pi session (Recommended)first. - Otherwise put
Start a new Pi session (Recommended)first. - If the user chooses continue, add
--resumebefore routing to the subagent. - If the user chooses a new session, add
--freshbefore routing to the subagent. - If the helper reports
available: false, do not ask. Route normally.
Operating rules:
- The subagent is a thin forwarder only. It should use one
Bashcall to invokenode "${CLAUDE_PLUGIN_ROOT}/scripts/pi-companion.mjs" task ...and return that command's stdout as-is. - Return the Pi companion stdout verbatim to the user.
- Do not paraphrase, summarize, rewrite, or add commentary before or after it.
- Do not ask the subagent to inspect files, monitor progress, poll
/pi:status, fetch/pi:result, call/pi:cancel, summarize output, or do follow-up work of its own. - Leave
--effortunset unless the user explicitly asks for a specific reasoning effort. - Leave the model unset unless the user explicitly asks for one.
--race <m1,m2,...>(2+ models) is a model race: the same task runs with every listed model in parallel and the output presents each racer's result so a winner can be picked. With--write, each racer runs in an isolated git worktree created from HEAD and its result is captured as a patch (git apply <patch>applies the winner). Preserve--racein the forwardedtaskcall. A race cannot be combined with--resume.- Leave
--resumeand--freshin the forwarded request. The subagent handles that routing when it builds thetaskcommand. - If the helper reports that Pi is missing or unconfigured, stop and tell the user to run
/pi:setup. - If the user did not supply a request, ask what Pi should investigate or fix.
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.
- 5d ago First seen · 52 lines · 19 tokens per session scan A 6a0dcff1651b
rescue is a command published in the GitHub repository Agents365-ai/pi-plugin-cc (44 stars, last pushed 20d ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,057 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 80% identical to rescue, differing in 46 lines, and is treated as a copy.
Other commands, from other repositories
review
Run a read-only Grok code review of your uncommitted changes or a branch.
search
Search X (Twitter) and the web in real time with Grok, then summarize with sources.
result
Show the final output of a completed Grok job.
kill
Stop a running cli-dispatch worker session.
cancel
Cancel a running background Grok job.
ag-run
Delegate a task to the Antigravity (agy / Gemini) worker.