web-search

web-search is a skill for Claude Code, Codex from ssube/conclave. It costs 52 tokens per session (368 once invoked), scanned A, original, MIT.

A web-search skill that retrieves current information from online sources and can fetch a specific webpage. It is intended for information that may have changed since the model was trained.

In plain words
What is it for?
Use it to look up current API documentation, investigate error messages, check platform changes, research news, or fetch answers from a specified URL.
Why use it?
General model knowledge can be outdated, especially for software documentation, platform rules, news, and error solutions. Searching provides newer information and source links.

Skill for Claude CodeCodex

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 skills/ssube/conclave/web-search
Any agent
npx skills add ssube/conclave --skill web-search
Clone the repo
git clone --depth 1 https://github.com/ssube/conclave

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 web-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/ssube/conclave/web-search.svg)](https://agentmods.dev/skills/ssube/conclave/web-search)
Your own site
<a href="https://agentmods.dev/skills/ssube/conclave/web-search"><img src="https://agentmods.dev/badge/skills/ssube/conclave/web-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 368 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 $0.00052 $0.00368
Opus 5 $0.00026 $0.00184
Sonnet 5 $0.00010 $0.00074
Haiku 4.5 $0.00005 $0.00037

Measured 3d ago against content hash 4eb130f4e985, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-search 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (search.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

pi/skills/web-search/SKILL.md · 57 lines

What it actually says

Web Search Skill

Search the web using Claude Code's built-in WebSearch and WebFetch tools. Returns concise summaries with source URLs.

Usage

Quick search (concise summary)

bash {baseDir}/search.sh "ComfyUI ControlNet union pro setup 2026"

Detailed search (multi-source analysis)

bash {baseDir}/search.sh --detailed "SDXL vs Flux LoRA training comparison"

Fetch a specific URL

bash {baseDir}/search.sh --fetch "https://docs.example.com/api" "What endpoints are available?"

When to Search vs When Not To

Search when:

  • Dates/versions matter (API changes, platform updates)
  • Error messages need current solutions
  • Platform policies may have shifted
  • You need documentation for a specific library version
  • Current events or news

Don't search when:

  • General programming patterns (you know these)
  • Information already in MEMORY.md or ChromaDB
  • Brand/creative decisions (those are internal)
  • Well-established tools with stable APIs

Cost

  • Quick search: ~$0.10-0.30 (Sonnet)
  • Detailed search: ~$0.30-1.00 (Sonnet)
  • URL fetch: ~$0.05-0.15 (Sonnet)

Uses Claude Sonnet by default for cost efficiency.

Environment

Requires claude CLI to be installed and authenticated.

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. 3d ago First seen · 57 lines · 52 tokens per session scan A 4eb130f4e985

Subscribe to this mod's changes

web-search is a skill published in the GitHub repository ssube/conclave (2 stars, last pushed 6mo ago), licensed MIT. It adds 52 tokens to every session and 368 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 skills, from other repositories

mine

Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.

MemPalace/mempalace · 21 tokens

mempalace-recall

Recall protocol for MemPalace — search the palace before answering about past work, people, projects, or prior decisions. Apply when the user asks what was decided, what happened before, who someone is, what was discussed last time, or anything that may already be filed in their memory palace; or when mempalace-recall…

MemPalace/mempalace · 94 tokens

docker-extend

Use when: User wants to extend Docker with custom tools, personalize the Docker environment, or set up user-specific Docker customization. Triggers: 'extend docker', 'docker-extend', 'add tools to docker', 'customize docker', 'add my tools to the container', 'personalize docker setup', 'docker user setup', 'install…

coleam00/Archon · 118 tokens

st-full-workflow

Use when the user asks to run the complete end-to-end Strikethroo workflow for a work order in one shot in this repository — triggers include full workflow, end-to-end, plan and execute, do everything, run the whole strikethroo workflow. Do not use when the user wants only one stage (create a plan, generate tasks, or…

e0ipso/strikethroo · 90 tokens

kami

Generate PDFs, resumes, CVs, letters, slide decks, portfolios, one-pagers, white papers, and professional documents. Use when user asks to create a PDF, make a resume, write a letter, design slides, format a document, typeset a report, build a portfolio, make a presentation, or create a one-pager. Warm parchment…

EliasOulkadi/shokunin · 0 tokens

st-code-review

Use when the blueprint execution gate asks for an independent second-harness review of a Strikethroo plan's cumulative diff in this repository — triggers include code review gate, review the plan diff, second-model review, CODEREVIEW hook, review the cumulative diff. Do not use to review a single task, to review code…

e0ipso/strikethroo · 87 tokens