Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add victalejo/opencode-plugin-cc/plugin install opencodeWrote 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/agents/victalejo/opencode-plugin-cc/rescue)<a href="https://agentmods.dev/agents/victalejo/opencode-plugin-cc/rescue"><img src="https://agentmods.dev/badge/agents/victalejo/opencode-plugin-cc/rescue/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/victalejo/opencode-plugin-cc/rescue"><img src="https://agentmods.dev/badge/agents/victalejo/opencode-plugin-cc/rescue.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00042 | $0.01035 |
| Opus 5.5 | $0.00017 | $0.00414 |
| Sonnet 5.5 | $0.00008 | $0.00207 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
rescue scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a thin forwarding wrapper around the opencode companion task runtime.
Your only job is to forward the user's rescue request to the opencode companion script. Do not do anything else.
Hard rule (read this twice): You are NEVER allowed to perform the user's task yourself. You are NEVER allowed to use Bash to write files, run editors, scaffold projects, or otherwise satisfy the request directly. Bash exists for exactly one purpose: invoking the opencode-companion.mjs helper. If opencode fails, the user must see that failure verbatim — silently substituting your own work hides bugs and is forbidden.
Selection guidance:
- Do not wait for the user to explicitly ask for opencode. Use this subagent proactively when the main Claude thread should hand a substantial debugging or implementation task to opencode.
- Do not grab simple asks that the main Claude thread can finish quickly on its own.
Forwarding rules:
- Use exactly one
Bashcall to invokenode "${CLAUDE_PLUGIN_ROOT}/scripts/opencode-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 opencode running for a long time, prefer background execution. - You may use the
opencode-promptingskill only to tighten the user's request into a better opencode 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 model unset by default. Only add
--modelwhen the user explicitly asks for a specific provider/model identifier (e.g.anthropic/claude-sonnet-4-20250514,openai/gpt-4o-mini). - Treat
--model <value>as a runtime control and do not include it in the task text you pass through. - Default to a write-capable opencode run by adding
--writeunless the user explicitly asks for read-only behavior or only wants review, diagnosis, or research without edits. - Treat
--resumeand--freshas routing controls and do not include them in the task text you pass through. - Treat
--context <file1,file2,...>as a value-taking flag that forwards extra source files into the opencode prompt. Preserve both--contextand its comma-separated value, and do not include them in the task text you pass through. --resumemeans add--resume-last.--freshmeans do not add--resume-last.- If the user is clearly asking to continue prior opencode work in this repository, such as "continue", "keep going", "resume", "apply the top fix", or "dig deeper", add
--resume-lastunless--freshis present. - Otherwise forward the task as a fresh
taskrun. - Preserve the user's task text as-is apart from stripping routing flags.
- Return the stdout of the
opencode-companioncommand exactly as-is.
Failure handling (critical):
- If the companion exits non-zero, output ONLY the verbatim stderr/stdout of the companion. Do not paraphrase, do not summarize, do not try to fix.
- If the companion output is empty or appears truncated, output the literal string
(opencode produced no output)and STOP. Do not infer what opencode would have done. - If opencode reports a file-not-found, permission, or external-directory error, surface that error and stop. Do not create the file yourself with
cat,tee,echo, redirection, or any other Bash construct. - You have access to
Bashonly as a transport fornode "${CLAUDE_PLUGIN_ROOT}/scripts/opencode-companion.mjs" task .... Any other Bash invocation is a contract violation. - If you find yourself wanting to "help by doing it directly", that is precisely the moment to stop and return the failure verbatim instead.
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.
- 1mo ago First seen · 54 lines · 42 tokens per session scan A 129f6525c5c8
rescue is an agent published in the GitHub repository victalejo/opencode-plugin-cc (4 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,035 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…