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 skills/m-ghalib/gemini-plugin-cc/gemini-cli-runtimenpx skills add m-ghalib/gemini-plugin-cc --skill gemini-cli-runtimegit clone --depth 1 https://github.com/m-ghalib/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/skills/m-ghalib/gemini-plugin-cc/gemini-cli-runtime)<a href="https://agentmods.dev/skills/m-ghalib/gemini-plugin-cc/gemini-cli-runtime"><img src="https://agentmods.dev/badge/skills/m-ghalib/gemini-plugin-cc/gemini-cli-runtime.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 | $0.01018 |
| Opus 5 | $0.00010 | $0.00509 |
| Sonnet 5 | $0.00004 | $0.00204 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
gemini-cli-runtime scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Gemini Runtime
Use this skill only inside the gemini:gemini-rescue subagent.
Primary helper:
node "${CLAUDE_PLUGIN_ROOT}/scripts/gemini-companion.mjs" task "<raw arguments>"
Execution rules:
- The rescue subagent is a forwarder, not an orchestrator. Its only job is to invoke
taskonce and return that stdout unchanged. - Prefer the helper over hand-rolled
git, direct Gemini CLI strings, or any other Bash activity. - Do not call
setup,review,adversarial-review,status,result, orcancelfromgemini:gemini-rescue. - Use
taskfor every rescue request, including diagnosis, planning, research, and explicit fix requests. - You may use the
gemini-3-promptingskill to rewrite the user's request into a tighter Gemini prompt before the singletaskcall. - That prompt drafting is the only Claude-side work allowed. Do not inspect the repo, solve the task yourself, or add independent analysis outside the forwarded prompt text.
- Leave
--effortunset unless the user explicitly requests a specific effort. The flag is accepted but has no effect yet (pending upstream ACP support for thinkingLevel). - Leave model unset by default. Add
--modelonly when the user explicitly asks for one. - Gemini model aliases:
pro→gemini-3.1-pro-previewpro-3→gemini-3.1-pro-preview(same aspro)flash→gemini-3-flash-previewflash-lite→gemini-3.1-flash-lite-preview2.5-pro→gemini-2.5-pro2.5-flash→gemini-2.5-flash2.5-flash-lite→gemini-2.5-flash-liteauto→auto-gemini-3auto-2.5→auto-gemini-2.5
- Default invocation mode for rescue is
--yolo --sandbox(Gemini CLI built-in sandbox, filesystem scoped to the working tree). Opt out with--plan(maps to--approval-mode plan, read-only).
Command selection:
- Use exactly one
taskinvocation per rescue handoff. - If the forwarded request includes
--backgroundor--wait, treat that as Claude-side execution control only. Strip it before callingtask, and do not treat it as part of the natural-language task text. - If the forwarded request includes
--model, normalize aliases from the table above and pass it through totask. - If the forwarded request includes
--effort, pass it through totask. Accepted values:low,medium,high(accepted; pending upstream ACP support for thinkingLevel). - If the forwarded request includes
--plan, pass it through totaskas a runtime flag. - If the forwarded request includes
--resume, strip that token from the task text and add--resume-last. - If the forwarded request includes
--fresh, strip that token from the task text and do not add--resume-last. --resume: always usetask --resume-last, even if the request text is ambiguous.--fresh: always use a freshtaskrun, even if the request sounds like a follow-up.task --resume-last: internal helper for "keep going", "resume", "apply the top fix", or "dig deeper" after a previous rescue run.
Safety rules:
- Default to write-capable Gemini work in
gemini:gemini-rescueunless the user explicitly asks for read-only behavior (pass--plan). - Preserve the user's task text as-is apart from stripping routing flags.
- Do not inspect the repository, read files, grep, monitor progress, poll status, fetch results, cancel jobs, summarize output, or do any follow-up work of your own.
- Return the stdout of the
taskcommand exactly as-is. - If the Bash call fails or Gemini cannot be invoked, return nothing.
ACP stability note:
- The Gemini ACP surface exposes methods like
session/new,session/prompt,session/cancel, andsession/unstable_setSessionModel. Theunstable_prefix signals the method name may change. If ACP calls start failing with method-not-found errors, edit the method-name table at the top oflib/acp-client.mjsrather than rewriting the broker.
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.
- 4d ago First seen · 56 lines · 19 tokens per session scan A d80fc0e67470
gemini-cli-runtime is a skill published in the GitHub repository m-ghalib/gemini-plugin-cc (19 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,018 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…