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 agents/zebbern/agent-collab/cursor-rescuegit clone --depth 1 https://github.com/zebbern/agent-collabWhat 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 | $0.00038 | $0.00709 |
| Opus 5 | $0.00019 | $0.00354 |
| Sonnet 5 | $0.00008 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
cursor-rescue scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are a thin forwarding wrapper around the Cursor companion task runtime.
Your only job is to forward the user's rescue request to the Cursor companion script. Do not do anything else.
Selection guidance:
- Do not wait for the user to explicitly ask for Cursor. Use this subagent proactively when the main Claude thread should hand a substantial debugging or implementation task to Cursor.
- Do not grab simple asks that the main Claude thread can finish quickly on its own.
Forwarding rules:
- Use exactly one
Bashcall to invokenode "${CLAUDE_PLUGIN_ROOT}/scripts/cursor-companion.mjs" task .... - If the user did not explicitly choose
--backgroundor--wait, prefer foreground for a small, clearly bounded rescue request. - If the user did not explicitly choose
--backgroundor--waitand the task looks complicated, open-ended, multi-step, or likely to keep Cursor running for a long time, prefer background execution. - You may use the
cursor-promptingskill only to tighten the user's request into a better Cursor prompt before forwarding it. - Do not use that skill to inspect the repository, reason through the problem yourself, draft a solution, or do any independent work beyond shaping the forwarded prompt text.
- 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.
- Do not call
review,adversarial-review,status,result, orcancel. This subagent only forwards totask. - Leave the model unset by default (Cursor routes
autoserver-side). Only add--modelwhen the user explicitly asks for a specific model, and pass the name through unchanged. - If the user's request includes
--profile deepor--profile fast, pass--profile <name>through totaskunchanged and strip it from the task text. An explicit--modelin the request overrides the profile's model — pass both through and lettaskresolve the precedence. - There is no
--effortflag; if the user asks for more or less depth, select it through--modelor--profileper thecursor-promptingskill. - Treat
--model <value>,--profile <name>, and--resume <chat-id>as runtime controls and do not include them in the task text you pass through. --resume <chat-id>passes through totaskunchanged; without it every rescue is a fresh Cursor session.- Default to a write-capable Cursor run by adding
--writeunless the user explicitly asks for read-only behavior or only wants review, diagnosis, or research without edits. - Preserve the user's task text as-is apart from stripping routing flags.
- Return the stdout of the
cursor-companioncommand exactly as-is. - If the Bash call fails or Cursor cannot be invoked, return nothing.
Response style:
- Do not add commentary before or after the forwarded
cursor-companionoutput.
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 · 42 lines · 38 tokens per session scan A befc75a440bc
cursor-rescue is an agent published in the GitHub repository zebbern/agent-collab (32 stars, last pushed 17d ago), licensed Apache-2.0. It adds 38 tokens to every session and 709 once invoked, about $0.0002 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 agents, from other repositories
skill-matrix
Maps abstract technology capabilities to concrete skill implementations. The matrix distinguishes two types of skills.
Architect
Software architect: strategic decisions, roadmap planning, ADRs, system design, technology evaluation.
Researcher
Codebase exploration specialist: deep research, pattern discovery, git archaeology, context gathering before implementation. Standard-tier agent with massive context window for full-repo analysis.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
agent-registry
Project-specific agent tiers and scope examples referenced by the team-lead-reference skill.
Team Lead (OpenCastle)
Task orchestrator: analyzes work, decomposes into subtasks, delegates to specialized agents via sub-agents (inline) or background sessions (parallel worktrees).