context-search

A guide for searching the live web through Context.dev and returning current findings with source links.

In plain words
What is it for?
Use it for research, recent announcements, articles, comparisons, and questions where the exact webpage is not already known.
Why use it?
It provides a repeatable way to find relevant sources while preserving dates, named entities, and other search limits.

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/context-dot-dev/cursor-plugin/context-search
Any agent
npx skills add context-dot-dev/cursor-plugin --skill context-search
Clone the repo
git clone --depth 1 https://github.com/context-dot-dev/cursor-plugin

Made for: Claude Code, Codex.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 229 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 $0.00053 $0.00229
Opus 5 $0.00026 $0.00114
Sonnet 5 $0.00011 $0.00046
Haiku 4.5 $0.00005 $0.00023

Measured yesterday against content hash 022f7215ba29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-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 yesterday.

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.

skills/context-search/SKILL.md · 21 lines

What it actually says

Search the live web

Use the Context.dev web-search MCP tool when the user needs source discovery or current information and does not already have the exact page URL.

Workflow

  1. Turn the request into a concise search query that preserves named entities, dates, and constraints.
  2. Set freshness or country only when the request calls for it.
  3. Use the smallest result count that can answer the question.
  4. Prefer authoritative or primary sources when the user asks for official information.
  5. Summarize the relevant findings and cite the returned source URLs.

If the user provides a known URL, use web-scrape-markdown instead. If a search result must be read in full, scrape only the selected result rather than every result.

Avoid repeating an identical search unless the first call failed or the query materially changed.

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. yesterday First seen · 21 lines · 53 tokens per session scan A 022f7215ba29

Subscribe to this mod's changes

context-search is a skill published in the GitHub repository context-dot-dev/cursor-plugin (4 stars, last pushed 14d ago), licensed MIT. It adds 53 tokens to every session and 229 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

systematic-debugging

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

obra/superpowers · 21 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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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