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/gemini-plugin-cc/rescuegit clone --depth 1 https://github.com/LovelaceLoom/gemini-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/lovelaceloom/gemini-plugin-cc/rescue)<a href="https://agentmods.dev/commands/lovelaceloom/gemini-plugin-cc/rescue"><img src="https://agentmods.dev/badge/commands/lovelaceloom/gemini-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 | $0.00653 |
| Opus 5 | $0.00010 | $0.00327 |
| Sonnet 5 | $0.00004 | $0.00131 |
| Haiku 4.5 | $0.00002 | $0.00065 |
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.
What it actually says
Invoke the gemini:gemini-rescue subagent via the Agent tool (subagent_type: "gemini:gemini-rescue"), forwarding the raw user request as the prompt.
The final user-visible response must be Gemini's output verbatim.
Raw user request: $ARGUMENTS
Execution mode:
- Default: run the
gemini:gemini-rescuesubagent in the foreground. A parent agent calling rescue expects a real answer, not a "job forwarded" stub. Backgrounding the subagent causes Claude Code's Bash tool to return immediately with a job ID, which the rescue wrapper would then forward verbatim instead of Gemini's actual output — that's the failure mode tracked in issue #3. - If the request includes
--background, the user has explicitly opted out of the synchronous contract; honor it and run the subagent in the background. They are responsible for following up with/gemini:statusand/gemini:result <id>themselves. --waitis accepted for backward compatibility but has no effect under the new default (foreground is already the default).--backgroundand--waitare execution flags for Claude Code. Do not forward them to the companion'stasksubcommand, and do not treat them as part of the natural-language task text.--writeand--read-onlyare runtime-selection flags. Preserve them for the forwardedtaskcall, but do not treat them as part of the natural-language task text.--modelis a runtime-selection flag. Preserve it for the forwardedtaskcall.
Operating rules:
- The subagent is a thin forwarder only. It should use one
Bashcall to invokenode "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" task ...and return that command's stdout as-is. - Default to read-only Gemini behavior. Add
--writeonly if the user explicitly asks for code changes or fixes to be applied. - Return the companion's 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
/gemini:status, fetch/gemini:result, call/gemini:cancel, summarize output, or do follow-up work of its own. - Do not call
review,adversarial-review,status,result, orcancel. This subagent only forwards totask. - If the helper reports that Gemini is missing or unauthenticated, stop and tell the user to run
/gemini:setup. - If the user did not supply a request, ask what Gemini 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 · 32 lines · 19 tokens per session scan A 7169b837465e
rescue is a command published in the GitHub repository LovelaceLoom/gemini-plugin-cc (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 653 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
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
wp-polylang
Translate an existing WordPress site into a second language using Polylang.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.