route-failed-searches-to-shell-agent

route-failed-searches-to-shell-agent is a skill for Claude Code, Codex from HKUDS/OpenSpace. It costs 35 tokens per session (1,118 once invoked), scanned A, original, MIT.

A fallback workflow that sends web-search work to another shell-based agent when the direct search tool fails. It can retry and try different collection methods.

In plain words
What is it for?
Collecting web-based information when direct search is unreliable, including retries and alternative methods.
Why use it?
It keeps multi-step information gathering moving after repeated search errors or incomplete results.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Collecting web-based information when direct search is unreliable, including retries and alternative methods.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hkuds/openspace/route-failed-searches-to-shell-agent
About the project

OpenSpace is a skill-management layer for AI agents that stores, retrieves, evaluates, shares, and improves reusable workflows. It is intended for people using multiple coding agents who want skills to be reused and refined based on task outcomes. The catalogue provides 200 skills for use with OpenSpace and the agents it supports.

HKUDS/OpenSpace · 7,552 stars · on GitHub

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.

Any agent
npx skills add HKUDS/OpenSpace --skill route-failed-searches-to-shell-agent
Clone the repo
git clone --depth 1 https://github.com/HKUDS/OpenSpace

Made for: Claude Code, Codex.

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 route-failed-searches-to-shell-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/hkuds/openspace/route-failed-searches-to-shell-agent/github.svg)](https://agentmods.dev/skills/hkuds/openspace/route-failed-searches-to-shell-agent)
Your own site
<a href="https://agentmods.dev/skills/hkuds/openspace/route-failed-searches-to-shell-agent"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/route-failed-searches-to-shell-agent/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 route-failed-searches-to-shell-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/hkuds/openspace/route-failed-searches-to-shell-agent"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/route-failed-searches-to-shell-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,118 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 37
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00035 $0.01118
Opus 5 $0.00017 $0.00559
Sonnet 5 $0.00007 $0.00224
Haiku 4.5 $0.00003 $0.00112

Measured 6d ago against content hash be390da38879, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

route-failed-searches-to-shell-agent scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Code-based solutions** - can write Python scripts, use curl, or other tools
benchmarks/gdpval/skills/route-failed-searches-to-shell-agent/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Route Failed Web Searches to Shell Agent

When to Use This Skill

Use this workflow when:

  • Direct search_web tool calls consistently fail with 'unknown error' or similar failures
  • You need to gather web-based information but the standard search tool is unreliable
  • The task requires multi-step data collection that benefits from autonomous retry logic
  • You need resilient data gathering that can adapt when initial approaches fail

Core Pattern

Instead of repeatedly calling search_web when it fails, delegate the entire search task to shell_agent. The shell_agent's internal capabilities provide:

  • Automatic retry logic with error detection and recovery
  • Multi-step approach - can try different methods (APIs, scraping, alternative sources)
  • Code-based solutions - can write Python scripts, use curl, or other tools
  • Autonomous adaptation - figures out the best approach without manual intervention

Step-by-Step Instructions

Step 1: Detect Search Tool Failure

When search_web returns errors like:

  • "unknown error"
  • Empty or incomplete results
  • Consistent failures across multiple queries

Recognize this as a signal to switch strategies rather than retrying the same failing tool.

Step 2: Delegate to Shell Agent

Create a task for shell_agent with clear objectives:

shell_agent(
    task="Gather current energy market data including oil prices, gas prices, and bond market information. Search multiple sources and compile findings into a structured summary.",
    timeout=300
)

Key task formulation principles:

  • Specify the what (data needed) not the how (specific tools to use)
  • Include success criteria and output format expectations
  • Allow sufficient timeout for multi-step execution (300+ seconds)
  • Let shell_agent decide whether to use Python, curl, or other approaches

Step 3: Verify Results

Check shell_agent output for:

  • Complete data collection (not partial results)
  • Multiple sources cited (indicates thorough searching)
  • Structured, usable output format
  • Evidence of error handling (mentions of retry attempts, alternative approaches tried)

Read the full file on GitHub · 143 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 143 lines · 35 tokens per session scan A be390da38879

Subscribe to this mod's changes

route-failed-searches-to-shell-agent is a skill published in the GitHub repository HKUDS/OpenSpace (7,552 stars, last pushed 28d ago), licensed MIT. It adds 35 tokens to every session and 1,118 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens