feat: add Bright Data agents for web intelligence and real-time web data

[felixLandlord]

Pull Request Checklist

• I have read and followed the CONTRIBUTING.md guidelines.
• I have read and followed the Guidance for submissions involving paid services.
• My contribution adds a new instruction, prompt, agent, skill, workflow, or canvas extension file in the correct directory.
• The file follows the required naming convention.
• The content is clearly structured and follows the example format.
• I have tested my instructions, prompt, agent, skill, workflow, or canvas extension with GitHub Copilot.
• I have run npm start and verified that README.md is up to date.
• I am targeting the staged branch for this pull request.

---

Description

This contribution adds two GitHub Copilot custom agents that connect Copilot to Bright Data's Web MCP server for live web intelligence:

• brightdata-rapid-agent — Real-time web research on Bright Data's free tier (5,000 requests/month). Uses discover, search_engine, scrape_as_markdown, and batch variants for search and page retrieval.
• brightdata-pro-agent — Full Bright Data MCP Pro mode with 60+ tools: everything in Rapid plus browser automation (scraping_browser_*), structured platform extractors (web_data_* for Amazon, LinkedIn, X, npm, etc.), and extract.

Both agents instruct Copilot to route all live web work exclusively through Bright Data MCP—not built-in web fetch or training data—and to cite tool output with title and URL. Users select the agent manually from the Copilot agent dropdown on github.com/copilot/agents, when assigning issues, in Copilot Chat /task, or via Copilot CLI (/agent or --agent=).

Setup: Add an Agents secret named COPILOT_MCP_BRIGHTDATA_TOKEN with a Bright Data API token. Requires a paid GitHub Copilot plan (Pro, Pro+, Business, or Enterprise). The Pro agent appends &pro=1 to the MCP URL for pay-as-you-go billing; Rapid uses the standard endpoint.

---

Type of Contribution

• New instruction file.
• New prompt file.
• New agent file.
• New plugin.
• New skill file.
• New agentic workflow.
• New canvas extension.
• Update to existing instruction, prompt, agent, plugin, skill, workflow, or canvas extension.
• Other (please specify):

---

Additional Notes

Paid service disclosure: Bright Data is a third-party paid service. The Rapid agent works on the free tier (5,000 MCP requests/month); Pro mode is usage-based. Users must create their own Bright Data account and supply their own API token via COPILOT_MCP_BRIGHTDATA_TOKEN. No credentials are embedded in the agent files.

MCP configuration: Agent-level mcp-servers in the YAML is used by Copilot cloud agent on GitHub.com. Copilot CLI users must configure the Bright Data MCP server locally with /mcp add; repository MCP settings do not carry over to CLI.

Testing: Agents were tested on GitHub.com cloud agent and Copilot CLI with live search, scrape, and (Pro) browser automation tasks. Both agents include retry and error-handling instructions for common MCP failures (502, timeout, empty body).

Official references:

• Bright Data MCP server
• GitHub custom agents configuration

---

By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🔍 Skill Validator Results

✅ All checks passed

Scope	Checked
Skills	0
Agents	2
Total	2

Severity	Count
❌ Errors	0
⚠️ Warnings	0
ℹ️ Advisories	0

Summary

Level	Finding
ℹ️	Found 2 agent(s)
ℹ️	Validated 2 agent(s)
ℹ️	✅ All checks passed (2 agent(s))

Full validator output

Found 2 agent(s)
Validated 2 agent(s)
✅ All checks passed (2 agent(s))

[github-actions]

🔒 PR Risk Scan Results

Scanned 3 changed file(s).

Severity	Count
🔴 High	0
🟠 Medium	0
ℹ️ Info	0

✅ No matching risk patterns were detected in changed files.

This is an automated soft-gate report. Findings indicate review targets and do not block merge by themselves.

[Copilot]

Pull request overview

Adds two new GitHub Copilot custom agents that configure and enforce using Bright Data’s MCP server for live web intelligence (Rapid/free tier vs Pro mode), and registers them in the generated agents documentation.

Changes:

• Added a Rapid-mode Bright Data web research agent with a constrained tool workflow and failure-handling guidance.
• Added a Pro-mode Bright Data web intelligence agent including guidance for web_data_*, extract, and scraping_browser_* tools.
• Updated docs/README.agents.md to include the two new agents and MCP install links.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 3 comments.

File	Description
docs/README.agents.md	Adds the two Bright Data agents to the generated agents table and includes MCP install links.
agents/brightdata-rapid-agent.agent.md	Introduces the Rapid (free-tier) Bright Data MCP-backed research agent definition and usage rules.
agents/brightdata-pro-agent.agent.md	Introduces the Pro Bright Data MCP-backed web intelligence agent definition and usage rules.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[aaronpowell]

Upon review, this is a little too heavily reliant on a paid service to fit into awesome copilot.