context-dev
Skill9 starsChanged 3 months agoMITView on GitHub
Build application code directly against the Context.dev REST API or SDKs with server-side API-key authentication. Use when the user asks to integrate Context.dev into a codebase, choose an SDK method or REST endpoint, debug an API request, or implement a backend Context.dev workflow. For ordinary live-web work inside Cursor, use the focused Context.dev MCP skills instead.
- Reads credentials
2 other projects use a version of this.
Adopted by
Most recently taken up by
- context-dot-dev/openclaw-contexttheir own version, first seen Oct 20, 2026
- context-dot-dev/claude-plugintheir own version, first seen Oct 17, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- context-dot-dev/claude-plugin★ 2same name
- context-dot-dev/openclaw-context★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- connect-context-devSkill
- context-batchesSkill
- context-brandSkill
- context-crawlSkill
- context-extractSkill
- context-monitorSkill
- context-parseSkill
- context-scrapeSkill
- context-searchSkill
- logolinkSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
Read the bearer token from CONTEXT_DEV_API_KEY.
- Distinctive: line 70
Do not use a general scrape when a purpose-built Brand or monitor operation already returns the required shape.
- Distinctive: line 176
Do not retry validation, permission, no-match, content-size, or unsupported-media failures unchanged.
- Distinctive: line 194
Before declaring an integration complete:
- Distinctive: line 198
Keep the API key on the server and prove the missing-key path is intentional.
- Distinctive: line 202
Run a focused success test and at least one relevant failure test.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Context.dev integration guide
Context.dev provides web scraping, URL mapping, crawling, web search and research, document parsing, and brand, people, and news data through https://api.context.dev/v1. One Scrape request can return any mix of nine outputs: Markdown, rendered HTML, a screenshot, images, original bytes, CSS-selected fields, highlights, JSON, and product data. Use the public OpenAPI document at docs.context.dev/openapi.json as the authority for paths, methods, parameters, and response fields.
Get access
- To call Context.dev from this agent session without writing code, connect the MCP server
https://mcp.context.dev/mcp. It signs in with OAuth in the user's browser and does not use an API key. Setup for each client: https://docs.context.dev/install-mcp.md - Application code and the CLI read an API key from
CONTEXT_DEV_API_KEY. If none is configured, follow https://www.context.dev/auth.md: register with the user's email, deliver the returned setup link and code to the user before polling, and store the key in an ignored environment file or secret manager without displaying it. Never ask the user to paste a key into chat. - Complete setup instructions: https://docs.context.dev/agent-quickstart.md
Keep credentials server-side
Read the bearer token from CONTEXT_DEV_API_KEY. Never print it, commit it, include it in browser code, or forward it to a target website.
export CONTEXT_DEV_API_KEY="ctxt_secret_..."
curl https://api.context.dev/v1/web/scrape \
-H "Authorization: Bearer $CONTEXT_DEV_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"url": "https://example.com",
"formats": { "markdown": true },
"sharedParams": { "mainContentOnly": true }
}'Route from input to operation
Choose the narrowest operation that directly returns the needed result.
| Input and desired result | Operation | Task guide |
| One URL to Markdown or rendered HTML | POST /web/scrape with formats.markdown or formats.html | Scrape |
| Known CSS selectors on one page to JSON | POST /web/scrape with formats.parse and parseParams.rules | Parse fields |
| One URL and a question to the most relevant passages | POST /web/scrape with formats.highlights and highlightsParams.query | Highlights |
| One URL and a JSON Schema to a structured object | POST /web/scrape with formats.json and jsonParams.schema | JSON |
| Exact URL to an inline PNG, JPEG, or WebP screenshot | POST /web/scrape with formats.screenshot | Screenshot |
| URL to image assets | POST /web/scrape with formats.images | Images |
| Resource URL to complete base64 bytes | POST /web/scrape with formats.bytes | Bytes |
| Product page to a product record with price, availability, images, and variants | POST /web/scrape with formats.product | Product |
| YouTube video URL to metadata and a timestamped transcript | POST /web/scrape with formats.markdown | YouTube |
| Page that needs clicks, scrolls, or waits before capture | POST /web/scrape with sharedParams.actions | Browser actions |
| Domain to its indexed URLs with page titles and descriptions | GET /web/urls | Map URLs |
| Starting URL to linked pages in one response, up to 500 pages | POST /web/crawl | Crawl |
| Starting URL or sitemap to a background crawl, up to 25,000 pages | POST /batch/submit with input.mode: "crawl" | Async crawls |
| URL list to Markdown or HTML in the background, up to 25,000 URLs | POST /batch/submit | Batches |
| Search query to ranked web results, optionally with Markdown or highlights | POST /web/search | Search |
| Research task to structured JSON and source URLs | POST /web/answers | Answers |
| Uploaded document up to 50 MiB to Markdown | POST /parse | Parse |
| Domain, name, work email, ticker, direct URL, or transaction descriptor to company profile | POST /brand/retrieve | Brand |
| Partial name or domain to matching indexed brands | GET /brand/search | Brand search |
| Domain or exact URL to design styles, font families, and available font files | GET /web/styleguide; read styleguide.typography and styleguide.fontLinks for fonts | Styleguide |
| Domain or work email known before a Brand or Styleguide request | POST /utility/prefetch | Prefetch |
| Person email, profile URL, or name plus company, school, or location to a person profile | POST /people/enrich (beta, paid plans) | People |
| Company name, domain, ticker, or ISIN to news articles | POST /news/search | News |
| URL or site to recurring change detection | /monitors operations | Monitors |
| Context.dev bug, docs mismatch, or friction you hit while integrating | POST /feedback | Agent feedback |
Do not use a general scrape when a purpose-built Brand or monitor operation already returns the required shape.
Verify the installed SDK before using it
| Language | Package | Client setup | Scrape and Map URLs |
| TypeScript | context.dev | new ContextDev({ apiKey: process.env.CONTEXT_DEV_API_KEY }) | client.web.scrape, client.web.mapUrls |
| Python | context.dev | ContextDev(api_key=os.environ["CONTEXT_DEV_API_KEY"]) | client.web.scrape, client.web.map_urls |
| Ruby | context.dev | ContextDev::Client.new(api_key: ENV.fetch("CONTEXT_DEV_API_KEY")) | client.web.scrape, client.web.map_urls |
| Go | github.com/context-dot-dev/context-go-sdk/v2 | Use the /v2 module; inspect its generated request model. | client.Web.Scrape, client.Web.MapURLs |
| PHP | context-dev/context-dev-php | Inspect the installed package version and generated method signature. | $client->web->scrape, $client->web->mapUrls |
- Go needs the
/v2module path forWeb.Scrape,Web.MapURLs, and the current Brand request body. - The PHP Brand helper can't express a single lookup type; use the SDK's low-level request method for Brand calls.
- Published packages can lag the API. If an installed scrape method doesn't accept
highlightsParams,jsonParams, orproductParams, send the request with the SDK's low-level request method. Do not invent generated types or pass fields the installed signature does not accept. - SDKs time out after 60 seconds per attempt (Go has no default timeout) and retry twice on connection errors,
408,409,429, and5xx. Raise the SDK timeout abovetimeoutOpts.millisecondsfor long requests.
For installation, runnable examples, and low-level request methods, read SDKs. For a first request and a trimmed response, read the Quickstart.
Scrape controls
formats: enable at least one ofhtml,markdown,screenshot,images,bytes,parse,highlights,json, orproduct. Outputs share one page visit. Each output hasrequested,success, anddata;successistruewhen retrieved,falsewhen retrieval fails, andnullwhen not requested. Failed outputs havedata: nulland do not discard successful outputs. Cost depends on the formats; see the cost table below.maxAgeMs: chooses acceptable cache age. Scrape and both scrape/crawl batches default to three days (259200000ms) and accept up to 365 days (31536000000ms). Synchronous Crawl defaults to one day and accepts up to 30 days. Set0to fetch fresh and refresh the requested outputs. Each Scrape output has its own cache key, so one response can combine cached outputs from different visits. Brand and Styleguide default to three months, accept0for a hard refresh, and clamp values above one year. The direct-URL and transaction Brand variants do not accept this control. Custom headers, actions, andzdrbypass cache reads and writes; otherwise inspectcache_metadata.status(hit,miss, orzdr) andage_ms.timeoutOpts: setmillisecondsup to 300,000 and choosebehavior: "fail"or"return-partial"where supported. Reaching the overall deadline with"fail"returns408. Scrape requires at least 5,000 ms forreturn-partialand marks partial captures or failed outputs withisPartial: true; individual outputs can fail under either behavior while others succeed. Crawl and Map URLs returnpartial: true. Prefetch is fail-only and Parse does not accepttimeoutOpts. See timeouts.maxPages,maxDepth,urlRegex, andstopAfterMs: bound crawl coverage, time, and credit exposure. Crawl capsmaxPagesat 500.sharedParams.mainContentOnly,includeSelectors,excludeSelectors, andincludeFrames: control page content before conversion. Exclusions win. Filters apply to HTML, Markdown, images, and parsed fields, never tobytes.formats.parsewithparseParams.rules: map each field name to a CSS selector string or{selector, type: "item" | "list", output: "text" | "html" | "@attribute" | nested rules}. Results arrive inparsed.data; missing items returnnulland missing lists return[]. Runs without an LLM.sharedParams.waitFor(milliseconds or a CSS selector; default 500 ms),settleAnimations, and browser actions (type: "perform" | "scroll" | "wait" | "waitFor", 1 to 5 per request): handle dynamic page state. Actions require a paid plan and bypass the cache. Action or selector failures can leave affected outputs withsuccess: false; verify the page state from successful captured outputs.formats.bytes: returns the original HTTP body as{contentType, base64}after decompression, up to 20 MiB decoded. Waiting, actions, and content filters never change it; requestformats.htmlfor rendered HTML.sharedParams.headersgo to the target origin only and are separate from the API bearer key.sharedParams.countryis a two-letter code for the network exit of the page fetch and image downloads; an unsupported code returns400before the scrape starts. See location and headers.screenshot.datais an inline data URL (data:image/png;base64,...) whenscreenshot.successistrue; otherwise it isnull. Choose the capture area withscreenshotParams.area(viewport,fullPage,{selector}, or a rectangle) up to 40 megapixels.zdr: "enabled": bypasses shared caches and retained content logs only when Zero Data Retention is enabled for the organization; otherwise the request fails with403.
Browser rendering and proxy routing improve access but do not guarantee that a page can be read. Preserve a fallback for WEBSITE_BLOCKED, login walls, missing content, and partial crawl results.
Map a website's URLs
GET /web/urls lists a site's URLs from Context.dev's index and adds stored title, description, keywords, and language where available. Pass domain without a protocol; narrow with urlRegex, maxLinks (default 10,000), includeSubdomains, or search (relevance-ordered). The SDK methods are client.web.mapUrls (TypeScript) and client.web.map_urls (Python, Ruby).
URLs without stored metadata return with only url and are queued for background enrichment, so a later request can include their metadata. Requests with zdr=enabled or credential-bearing target headers return URLs only and do not queue enrichment. partial: true means the deadline stopped URL mapping. Feed the result into Scrape, Crawl, or a batch.
Retrieve brand data
Send exactly one lookup variant:
type | Required field | Important constraint |
by_domain | domain | Prefer a bare company domain. |
by_name | name | 3 to 30 characters; use country_gl as an ambiguity hint. |
by_email | email | Free and disposable providers return 422. |
by_ticker | ticker | Add ticker_exchange when known. |
by_direct_url | direct_url | Reads only that page; no wider resolver or cross-source enrichment. |
by_transaction | transaction_info | Add MCC, city, country, or phone hints when available. |
const response = await client.brand.retrieve({ type: "by_domain", domain: "stripe.com" });
const title = response.brand?.title ?? "Unknown company";An uncached domain or email lookup with behavior: "fail" and timeoutOpts.milliseconds under 10,000 returns 422 COLD_DOMAIN_TIMEOUT_TOO_LOW; allow 60,000 ms or prefetch. Brand arrays and nested fields can be missing or empty. Select logos by type, mode, and resolution; do not assume logos[0] is appropriate. Treat address, contacts, employee count, classifications, and stock data as discovered data rather than verified legal records.
Permissions and other operation notes
- Restricted API keys need the relevant scope:
data:executefor direct data calls, Read/Manage scopes for monitors and batches, andlogs:readfor request logs. Any key can submit Agent Feedback. Dashboard team roles are independent; Members can use shared credentials and incur charges. - Answers defaults to
ultramode;fastis cheaper and quicker.json_formatis an example object, and source URLs are not per-field citations. - Scrape, Map URLs, Crawl, Search, Answers, Parse, People Enrich, and Styleguide honor
zdrwhen the organization is entitled. - Page monitors accept
include_selectors/exclude_selectors; changing them establishes a new baseline.
Budget requests
| Operation | Credits |
POST /web/scrape | 1, or 2 with sharedParams.actions. Highlights +1 when passages are returned; JSON +4 on success; product +1 on success or a missing page; PDF OCR +1 per recovered page on a fresh fetch. 0 when every output fails, except a target 404, which charges the base (+1 with product). |
GET /web/urls | 1, or 2 with search |
POST /web/crawl | 1 per page; rate-limit weight 10 on per-minute plans |
POST /web/search | 1 per 10 results; Markdown and highlights each add 1 per 10 results when returned |
POST /web/answers | 10 (fast) or 100 (ultra, the default), charged only on success |
POST /parse | 1, plus 1 per OCR-recovered page |
POST /brand/retrieve, GET /web/styleguide | 10 |
GET /brand/search | 1; free on Pro, Growth, and Scale |
POST /people/enrich | 20 per match; paid plans |
POST /news/search | 1 per 10 results |
POST /utility/prefetch | 0; paid plans |
POST /batch/submit | 1 per page: 1 reserved per accepted URL (a crawl reserves maxUrls), refunded for pages that don't succeed, plus 1 per OCR-recovered PDF page |
POST /monitors, POST /monitors/{id}/run | Per run: 1 for a page or sitemap monitor, 10 for an extract monitor. Baseline runs, at creation or after a re-baseline, are charged; failed and skipped runs are free. |
Other batch and monitor operations, webhook deliveries, request logs, POST /feedback | 0 |
Processed 404 results on priced data APIs and successful partial results are charged. Validation, authentication, rate-limit, timeout, and server errors are not. Record key_metadata.credits_consumed or the X-Credits-Used header instead of inferring cost from status. Plan allowances are on Credits and pricing.
Handle errors by category
Inspect both the HTTP status and error_code for request errors. Scrape also reports output failures inside 200 responses: inspect each output's success and preserve isPartial: true. Use raw HTTPS or the SDK's raw response if an older generated model does not expose these fields.
| Status | Treat as | Action |
400 | Invalid request, inaccessible or blocked target on operations that fetch one directly (WEBSITE_ACCESS_ERROR, WEBSITE_BLOCKED), image-only PDF on Parse (PDF_IMAGES_ONLY), skipped PDF (PDF_SKIPPED), or no match, depending on error_code | Fix the input or options. For PDF_IMAGES_ONLY, retry Parse with ocr=true. Use a fallback for a no-match or inaccessible site. |
401 | Missing or unknown key (NOT_FOUND), disabled key (DISABLED), or not enough credits (USAGE_EXCEEDED) | Fix the key or account state; do not retry unchanged. |
403 | Missing key scope (INSUFFICIENT_PERMISSIONS, with required_permission), paid-plan feature (PAID_PLAN_REQUIRED), too many active batches (BATCH_LIMIT_EXCEEDED), or ZDR not enabled (ZDR_NOT_ENABLED) | Do not retry unchanged; inspect error_code. |
404 | Target or entity not found on operations that define it | Treat as an expected empty outcome where appropriate. |
408 | The request reached timeoutOpts.milliseconds with behavior: "fail" (REQUEST_TIMEOUT) | Retry outside a user-facing path, raise the budget, use return-partial where supported, or prefetch supported Brand and Styleguide requests. |
200 with a failed Scrape output | Retrieval, parsing, actions, selectors, or output limits prevented that output from completing | Preserve successful outputs and fix the target or options before retrying the failed output. Oversized outputs have success: false and data: null. |
413, 415 | Content too large (such as a Parse upload over 50 MiB) or unsupported, on operations that define these errors | Use a smaller or supported input. Scrape marks such outputs as failed instead. |
422 | An operation-specific input restriction, such as a free email domain or a Brand timeout that is too low | Change the input or options; do not retry unchanged. |
429 | Organization concurrency limit, or the API key's per-minute limit on older plans | Honor Retry-After; keep parallel calls within the concurrency limit and retry with jittered, bounded backoff. |
500, 502, 503 | Transient failure: a service error, an incomplete browser capture, or no browser capacity | Retry with jittered, bounded backoff, then surface a fallback. |
Do not retry validation, permission, no-match, content-size, or unsupported-media failures unchanged. The SDKs already retry twice; account for that before adding another retry layer. See Troubleshooting and Rate limits for operation-specific behavior.
Report problems with Agent Feedback
When an endpoint, docs page, SDK, or CLI behaves differently than documented, offer to report it with Agent Feedback: POST https://api.context.dev/v1/feedback with the same bearer key. It works with any API key and has its own rate limit. Send one report per problem with the affected request_id so the team can see the exact request, and keep secrets and personal data out of the note.
{
"request_id": "<request_id from the affected response>",
"category": "docs_mismatch",
"note": "The response is missing a documented field; expected it per the API reference."
}Send url instead of, or with, request_id for a docs page or one page of a crawl. Categories are bug, docs_mismatch, friction, feature_gap, quality_degradation, and other. Reporting the same request_id again returns the original feedback_id with already_submitted: true. In an MCP session, use the submit-feedback tool instead.
Completion checklist
Before declaring an integration complete:
- Confirm the path, method, and parameter names against the current API reference.
- Request only the
formatsthe task needs, and read each output'sdatarather than assuming it is present. - Keep the API key on the server and prove the missing-key path is intentional.
- Bound crawl size, latency, retries, and credit exposure.
- Handle missing fields and expected no-result states.
- Validate parsed and structured output and preserve provenance when needed.
- Run a focused success test and at least one relevant failure test.
For long-lived integrations, read Security and API stability and the changelog.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

