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 skills add KingGyuSuh/gemini-search-cc --skill search-result-handlinggit clone --depth 1 https://github.com/KingGyuSuh/gemini-search-ccWrote 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/skills/kinggyusuh/gemini-search-cc/search-result-handling)<a href="https://agentmods.dev/skills/kinggyusuh/gemini-search-cc/search-result-handling"><img src="https://agentmods.dev/badge/skills/kinggyusuh/gemini-search-cc/search-result-handling/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/skills/kinggyusuh/gemini-search-cc/search-result-handling"><img src="https://agentmods.dev/badge/skills/kinggyusuh/gemini-search-cc/search-result-handling.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 | $0.00011 | $0.00436 |
| Opus 5 | $0.00005 | $0.00218 |
| Sonnet 5 | $0.00002 | $0.00087 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
search-result-handling 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 12d 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
Search Result Handling — Internal Skill
This skill provides guidance on how to handle and present the search results within the Claude Code conversation.
Principles
-
Verbatim first. Always present the raw search output before any analysis. The user should see exactly what the search returned.
-
Do not paraphrase search results. If the search says "React 19.1.0 was released on March 2026", do not rephrase it as "a recent version of React was released."
-
Cite what the search cited. If the search output includes URLs or source names, preserve them. Do not invent additional citations.
-
Additive analysis only. After showing raw results, you may add:
- A brief summary of key points (3 bullets max)
- Relevance to the user's current task
- Suggested follow-up actions
-
Severity ordering. When multiple findings exist, present them in order: Critical > High > Medium > Low > Informational
-
Never auto-fix. Search results may suggest updates or changes. Present the recommendation but never automatically apply changes to the codebase.
-
Stale result awareness. If search results seem outdated or contradictory, flag this to the user and suggest re-running the search.
Mode-Specific Guidance
- search/research: Highlight version numbers, dates, and source agreement
- audit: Sort findings by severity (Critical > High > Medium > Low)
- factcheck: Lead with the verdict (Confirmed / False / etc.) before evidence
- changelog: Emphasize breaking changes and migration requirements
- compare: Present both options fairly; recommend based on evidence, not preference
When Search Fails
- Show the error clearly
- Run
/gemini:setupto diagnose - Suggest alternative approaches (different query, manual search)
- Do not pretend the search succeeded
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.
- 12d ago First seen · 49 lines · 11 tokens per session scan A 06076bc0e77f
search-result-handling is a skill published in the GitHub repository KingGyuSuh/gemini-search-cc (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 436 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.
Other skills, from other repositories
notebook-kb
Use the notebook knowledge base (the local SQLite RAG /agy:notebook builds from a folder of documents) to do precise, grounded, cited work — total amounts by category, find every doc that mentions a person/organization, build a timeline, export a table — instead of re-reading prose and burning Claude's context.…
agy-prompting
Internal helper — how to tighten a user request into a sharp prompt for the Antigravity CLI (agy / Gemini 3.x with native web search and agentic tools).
provider-integration
Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface. Covers creating provider shell scripts, setting API keys, and validating connectivity. Triggers on "add provider", "new AI agent", "provider not working", "API…
librarium
Runs evidence-aware, multi-provider research with the Librarium v2 CLI. Use for deep research, competitive research, answer-engine visibility checks, or questions needing grounded multi-source coverage.
video-perception
Use when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation.
autosearch:channel-selection
Group-first channel selection algorithm for v2 tool-supplier architecture. Given a research query + clarify rubrics + channelpriority hints, picks 1-3 relevant groups from the router index, then 3-8 leaf channels from within those groups. Replaces flat-rank selection across 41 channels with a two-stage pick so runtime…