ds-rescue

ds-rescue is an agent for Claude Code from zred0627/ds-rescue-cc. It costs 60 tokens per session (1,378 once invoked), scanned A, original, MIT.

An agent that forwards plans, technical designs, or code changes to the ds-rescue program for a DeepSeek adversarial review. It supports plan, scheme, and execution modes, with automatic mode detection.

In plain words
What is it for?
Use it when you want DeepSeek to challenge a plan, inspect a design, or review the latest Git changes.
Why use it?
It adds a cross-family second opinion and returns the review findings without rewriting or filtering them.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable. Also seen: model in frontmatter; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ds-rescue plugin — 1 skill, 1 command, 1 agent, 1 hook shipped together

Good fit Use it when you want DeepSeek to challenge a plan, inspect a design, or review the latest Git changes.

Compare 6 agents from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add zred0627/ds-rescue-cc
Claude Code
/plugin install ds-rescue

Made for: Claude Code.

Or install ds-rescue, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent, 1 hook.

Wrote 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.

agentmods badge for ds-rescue

README.md
[![agentmods](https://agentmods.dev/badge/agents/zred0627/ds-rescue-cc/ds-rescue/github.svg)](https://agentmods.dev/agents/zred0627/ds-rescue-cc/ds-rescue)
Your own site
<a href="https://agentmods.dev/agents/zred0627/ds-rescue-cc/ds-rescue"><img src="https://agentmods.dev/badge/agents/zred0627/ds-rescue-cc/ds-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.

agentmods 80×15 button for ds-rescue

Your own site · 80×15
<a href="https://agentmods.dev/agents/zred0627/ds-rescue-cc/ds-rescue"><img src="https://agentmods.dev/badge/agents/zred0627/ds-rescue-cc/ds-rescue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,378 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00060 $0.01378
Opus 5 $0.00030 $0.00689
Sonnet 5 $0.00012 $0.00276
Haiku 4.5 $0.00006 $0.00138

Measured 9d ago against content hash 12b7763f967a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ds-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 9d 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.

plugins/ds-rescue/agents/ds-rescue.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DS Rescue Agent

You are a thin forwarder to the ds-rescue Go binary. Your job is to:

  1. Resolve the binary path: check $CLAUDE_PLUGIN_ROOT/bin/ds-rescue{,.exe} first; fall back to which ds-rescue. If neither found, instruct the user to run the install hook (/ds-rescue:install) or download from https://github.com/zred0627/ds-rescue-cc/releases.
  2. Inspect the user's input. If they pass a flag (--plan, --scheme, --execution), honor it. If they pass a file path without a flag, let the binary auto-detect mode. If they ask for an execution-mode review, the binary internally runs git diff HEAD~1 HEAD — do NOT pass a diff payload.
  3. Set DS_RESCUE_SKILL_PATH=$CLAUDE_PLUGIN_ROOT/skills/ds-plan-challenger/SKILL.md so the binary loads the bundled three-mode persona.
  4. Invoke ds-rescue via Bash and return its stdout verbatim. Do not edit, summarize, or filter findings — they're meant to be raw second-opinion adversarial output.

When to invoke

  • User explicitly asks for a DeepSeek review or "second opinion"
  • User says /ds-rescue ... (the slash command auto-dispatches to me)
  • After Claude Code produces a plan and the user wants cross-family scrutiny
  • Post-commit when the user wants Plan vs Diff conformance check

How to invoke (canonical command shape)

DS_RESCUE_SKILL_PATH="$CLAUDE_PLUGIN_ROOT/skills/ds-plan-challenger/SKILL.md" \
  "$CLAUDE_PLUGIN_ROOT/bin/ds-rescue" \
  --mode <plan|scheme|execution> \
  --model pro \
  <input-file-if-not-execution>

For execution mode (no input file):

DS_RESCUE_SKILL_PATH="$CLAUDE_PLUGIN_ROOT/skills/ds-plan-challenger/SKILL.md" \
  "$CLAUDE_PLUGIN_ROOT/bin/ds-rescue" --mode execution

Bash tool parameters (MUST set explicitly)

The Go binary's internal -api-timeout defaults to 600s. Claude Code's Bash tool defaults to 120s — if you don't override it, a healthy DeepSeek round can be killed mid-flight and your wrapper will see an opaque timeout. Always pass:

  • timeout: 600000 (10 minutes in milliseconds — matches the binary's -api-timeout=600)
  • run_in_background: false (synchronous stdout is required)

Read the full file on GitHub · 117 lines

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. 9d ago First seen · 117 lines · 60 tokens per session scan A 12b7763f967a

Subscribe to this mod's changes

ds-rescue is an agent published in the GitHub repository zred0627/ds-rescue-cc (2 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 1,378 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

reviewer

Code reviewer (escalation, not a default step). Use for code reviews, finding bugs, assessing quality, and reviewing PRs/changes. Never modifies code.

znlgis/my-opencode-deepseek-config · 37 tokens

spec-reviewer

Use this agent when Terraform code needs to be validated against the design specification (design.md). This agent checks that every requirement in the design is correctly implemented in the generated code. Dispatched by the alibabacloud:validate skill during Stage 1 validation.

aliyun/alibabacloud-agent-toolkit · 57 tokens

sentinel

Security reviewer for a code change — finds vulnerabilities and attack surfaces (OWASP Top 10, secrets, injection, authz). Use when reviewing a diff/PR for security, or as the security lens in a parallel review.

Alexander-Tyagunov/magician · 49 tokens

simplifier

Simplification reviewer for a code change — finds over-engineering, premature abstraction, and unnecessary complexity. Use when reviewing a diff/PR for simplification, or as the simplification lens in a parallel review.

Alexander-Tyagunov/magician · 45 tokens

verifier

Test/verification reviewer for a code change — ensures correctness is proven, not assumed (coverage, edge cases, meaningful assertions). Use when reviewing test quality for a diff/PR.

Alexander-Tyagunov/magician · 39 tokens

reviewer

Code review agent. Use for reviewing code changes before push/merge, checking for bugs, security issues, and ensuring quality standards. Mandatory before any push.

randomittin/heimdall · 34 tokens