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/vit129/agy-plugin-cc/rescuegit clone --depth 1 https://github.com/Vit129/agy-plugin-ccWhat 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 | $0.00023 | $0.00708 |
| Opus 5 | $0.00012 | $0.00354 |
| Sonnet 5 | $0.00005 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
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 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
Invoke the agy:agy-rescue subagent via the Agent tool (subagent_type: "agy:agy-rescue"), forwarding the raw user request as the prompt.
agy:agy-rescue is a subagent, not a skill — do not call Skill(agy:agy-rescue). The command runs inline so the Agent tool stays in scope.
The final user-visible response must be agy's output verbatim.
Raw user request: $ARGUMENTS
Execution mode:
- If the request includes
--background, run theagy:agy-rescuesubagent in the background. - If the request includes
--wait, run it in the foreground. - If neither flag is present, default to foreground.
--backgroundand--waitare execution flags for Claude Code. Do not forward them to the task text.--sandbox,--model, and--effortare runtime flags. Preserve them for the forwarded call but do not treat them as part of the natural-language task text.- If the request includes
--continue, do not ask whether to continue. The user already chose. - If the request includes
--fresh, do not ask whether to continue. The user already chose. - Otherwise, before starting agy, check for a resumable session by running:
node "${CLAUDE_PLUGIN_ROOT}/scripts/agy-companion.mjs" task-resume-candidate --json
- If that helper reports
available: true, useAskUserQuestionexactly once to ask whether to continue the current agy conversation or start a new one. - The two choices must be:
Continue current agy conversationStart a new agy conversation
- 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 agy conversation (Recommended)first. - Otherwise put
Start a new agy conversation (Recommended)first. - If the user chooses continue, add
--continuebefore routing to the subagent. - If the user chooses a new conversation, 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 uses one
Bashcall to invokenode "${CLAUDE_PLUGIN_ROOT}/scripts/agy-companion.mjs" task ...and returns that stdout as-is. - Return the agy output verbatim to the user.
- Do not paraphrase, summarize, rewrite, or add commentary before or after it.
- If the helper reports that agy is missing or unauthenticated, stop and tell the user to run
/cc-agy-plugin:setup. - If the user did not supply a request, ask what agy 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.
- 2d ago First seen · 46 lines · 23 tokens per session scan A c54ae3da8b33
rescue is a command published in the GitHub repository Vit129/agy-plugin-cc (5 stars, last pushed 9d ago), licensed MIT. It adds 23 tokens to every session and 708 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
adversarial-review
Run an adversarial Gemini code review that challenges the implementation approach and design choices.
review
Run a standard Gemini code review of recent git changes.
result
Show the stored final output for a finished Gemini job in this repository.
status
Show active and recent Gemini jobs for this repository, including review-gate status.
cancel
Cancel an active background Gemini job in this repository.
image
Generate an image with Antigravity CLI (uses agy's built-in generateimage tool — Imagen under the hood).