agentmods.dev

rescue

A command for sending an investigation, repair or follow-up task to a separate OpenCode rescue agent. It forwards the original request and can run the work in the foreground or background.

In plain words
What is it for?
Use it to delegate rescue work, choose whether to wait for the result, run it in the background, or resume or start a task afresh.
Why use it?
It provides a way to delegate work when a task needs additional investigation or recovery. The available options also control whether to resume an earlier task and how it runs.

Command

1 3mo ago A scan 18 tokens original MIT
View the source file skillsland/opencode-plugin-cc
Install

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.

agentmods
npx agentmods add commands/skillsland/opencode-plugin-cc/rescue
Clone the repo
git clone --depth 1 https://github.com/skillsland/opencode-plugin-cc
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 807 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.00807
Opus 5 $0.00009 $0.00404
Sonnet 5 $0.00004 $0.00161
Haiku 4.5 $0.00002 $0.00081

Measured yesterday against content hash 7f85f9ff11e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

commands/rescue.md · 49 lines

What it actually says

Invoke the opencode:opencode-rescue subagent via the Agent tool (subagent_type: "opencode:opencode-rescue"), forwarding the raw user request as the prompt. The final user-visible response must be OpenCode's output verbatim.

Raw user request: $ARGUMENTS

Execution mode:

  • If the request includes --background, run the opencode:opencode-rescue subagent in the background.
  • If the request includes --wait, run the opencode:opencode-rescue subagent in the foreground.
  • If neither flag is present, default to foreground.
  • --background and --wait are Claude-side execution flags. Do not treat them as natural-language task text.
  • --model, --variant, --write, and --dangerously-skip-permissions are runtime controls. Preserve them for the forwarded task call, but do not treat them as natural-language task text.
  • 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 OpenCode, check for a resumable task for this repository by running:
node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/opencode-companion.mjs" task-resume-candidate --json
  • If that helper reports available: true, use AskUserQuestion exactly once to ask whether to continue the current OpenCode thread or start a new one.
  • The two choices must be:
    • Continue current OpenCode thread
    • Start a new OpenCode thread
  • 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 OpenCode thread (Recommended) first.
  • Otherwise put Start a new OpenCode thread (Recommended) first.
  • If the user chooses continue, add --resume before routing to the subagent.
  • If the user chooses a new thread, add --fresh before 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 Bash call to invoke node "${CLAUDE_PLUGIN_ROOT}/dist/scripts/opencode-companion.mjs" task ... and return that command's stdout as-is.
  • Return the OpenCode 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 /opencode:status, fetch /opencode:result, call /opencode:cancel, summarize output, or do follow-up work of its own.
  • Leave model and variant unset unless the user explicitly asks for one.
  • Default to read-only unless the user asks for fixes or passes --write; for explicit fix/implementation requests, include --write.
  • Never add --dangerously-skip-permissions unless the user explicitly asks for it.
  • If the helper reports that OpenCode is missing or unauthenticated, stop and tell the user to run /opencode:setup.
  • If the user did not supply a request, ask what OpenCode should investigate or fix.
Changes

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.

  1. yesterday First seen · 49 lines · 18 tokens per session scan A 7f85f9ff11e5

Subscribe to this mod's changes

rescue is a command published in the GitHub repository skillsland/opencode-plugin-cc (1 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 807 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.

Building agentsPlanningResearchclaude-codeclaude-code-pluginopencode
Related

Other commands, from other repositories

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

hamr0/liteagents · 45 tokens

distill

Distill hot-tier model observations into the committed capability cards and the SKILL.md rankings block.

Buckeyes22/subagent-model-routing · 19 tokens

run

Execute a named subagent with optimized instructions.

mystilleef/spae-framework · 9 tokens

release

This compatibility command keeps /oh-my-claudecode:release available without loading the full release skill description in every Claude Code session.

Yeachan-Heo/oh-my-claudecode · 0 tokens

research

Research a technical or product question.

jcarlosrodicio/opencode-agent-orchestration-kit · 7 tokens

no-vibe

Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).

rizukirr/no-vibe · 19 tokens