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 dunkeln/bright_mcp --skill bright-web-intelligencegit clone --depth 1 https://github.com/dunkeln/bright_mcpWrote 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/dunkeln/bright_mcp/bright-web-intelligence)<a href="https://agentmods.dev/skills/dunkeln/bright_mcp/bright-web-intelligence"><img src="https://agentmods.dev/badge/skills/dunkeln/bright_mcp/bright-web-intelligence.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.00638 |
| Opus 5 | $0.00034 | $0.00319 |
| Sonnet 5 | $0.00013 | $0.00128 |
| Haiku 4.5 | $0.00007 | $0.00064 |
Grade A, and why
bright-web-intelligence 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bright Web Intelligence
Use the narrowest Bright MCP tool that directly matches the requested outcome.
Route by intent
| Source state | Requested outcome | Tool |
|---|---|---|
| Unknown | Compact links and summaries | search_web |
| Unknown, constrained by a goal | Ranked source shortlist | discover_web |
| Known URLs | Readable evidence | read_web |
| Known URLs | Exact source markup | read_web with representation: source |
| Known URLs | Temporary named fields | extract_web |
| Unknown | Sourced structured records | research_web |
| Maintained vertical data | Typed records | find_datasets, then run_dataset |
Do not replace research_web with repeated search-and-read calls when the user
asked for a sourced structured table. Do not call find_datasets when ordinary
web evidence is sufficient.
Treat the connection's advertised tools as authoritative. If Deep Lookup returns
upstream_capability_unavailable, follow its search_web and read_web fallback
once; do not retry research_web or extract_web.
Execute
- Infer source certainty and output shape from the request.
- Call one chart-ready or answer-ready tool first; avoid probe calls that do not advance the task.
- Batch related queries or known URLs within the tool limits.
- Keep preview mode for Deep Lookup unless the user explicitly accepts a full paid run and supplies the required cost cap.
- Follow returned resource URIs for complete content or continuation pages; never invent cursors or expose opaque values as user input.
- Cite returned sources and state when evidence is incomplete, truncated, or only a ranked shortlist.
Handle results
- Treat
extract_web,research_web, andrun_datasetoutput as the canonical dataset result. Do not reinterpret upstream field names. - Let compatible clients render the attached Dataset Workbench automatically. Never search for or invoke the MCP App as a separate tool.
- Use the workbench for human filtering, sorting, paging, inspection, quality, provenance, export, and bounded row selection.
- Continue to provide a useful text answer when the client does not render MCP Apps.
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.
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.
- 7d ago First seen · 63 lines · 67 tokens per session scan A ef6b6e7862aa
bright-web-intelligence is a skill published in the GitHub repository dunkeln/bright_mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 638 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…