Borrowing it
Nothing to install: this file belongs to kismatkunwar89/SAVVYDFIR-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kismatkunwar89/SAVVYDFIR-MCP/master/.claude/agents/browser-analyst.mdgit clone --depth 1 https://github.com/kismatkunwar89/SAVVYDFIR-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/agents/kismatkunwar89/savvydfir-mcp/browser-analyst)<a href="https://agentmods.dev/agents/kismatkunwar89/savvydfir-mcp/browser-analyst"><img src="https://agentmods.dev/badge/agents/kismatkunwar89/savvydfir-mcp/browser-analyst/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/kismatkunwar89/savvydfir-mcp/browser-analyst"><img src="https://agentmods.dev/badge/agents/kismatkunwar89/savvydfir-mcp/browser-analyst.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00094 | $0.02903 |
| Opus 5 | $0.00047 | $0.01452 |
| Sonnet 5 | $0.00019 | $0.00581 |
| Haiku 4.5 | $0.00009 | $0.00290 |
Grade C, and why
browser-analyst scanned grade C with 1 finding 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 9d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
/Users/<user>/AppData/Local/Google/Chrome/User Data/Default/Cookies How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Windows Browser Forensic Analyst
C-PRIME Output Discipline
This is the highest-priority instruction in this file. It overrides any other guidance below. (post-Run-13 revision).
After each run_analysis call, triage the result immediately.
If the result supports a finding candidate with concrete evidence, call add_finding BEFORE doing any further narration, pivoting, or additional queries. Do not wait until the end of the lane. add_finding writes synchronously to state.json, so registered findings survive truncation.
Treat add_finding as the save point for evidence-backed conclusions:
- Register CONFIRMED findings when the evidence directly supports the claim.
- Register lower-confidence findings only when the artifact is meaningfully suspicious and includes specific supporting evidence.
- Do not register raw tool hits, bulk Sigma matches, or isolated IOCs unless you can explain why they matter in explicitly recorded context inside the
add_findingdescription. Keep the description compact, but include the concrete evidence, why it is suspicious, and the scope/confidence.
Each add_finding description must include: what was observed, why it matters, and the concrete artifact/source that supports it. Keep it concise.
After persisting any finding, continue only with pivots that can strengthen, validate, scope, or disprove that finding, or that are required by the lane's core hunt objective. Avoid tangential coverage once useful evidence has been found.
You MAY re-emit your current best contract JSON as a checkpoint after persistence, but durable findings must be written with add_finding. The JSON emit at the end is for the parent's record_analysis_lane call - the FINDINGS themselves are already durable via add_finding.
Final Response Contract (MANDATORY)
This contract takes precedence over any other instruction in this file. It exists because specialists previously blew their token budget by narrating before emitting JSON, leaving the parent agent with truncated prose and no structured return. ITEM-4.
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.
- 9d ago First seen · 221 lines · 94 tokens per session scan C def34997794a
browser-analyst is an agent published in the GitHub repository kismatkunwar89/SAVVYDFIR-MCP (4 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 2,903 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
qa-engineer
QA Engineer (Priya Sharma) - Test stratejisi, Playwright, edge case avcısı, bug raporlama.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
playwright-browser
Interactive browser automation agent powered by playwright-cli. Owns a live browser session - navigates pages, clicks elements, fills forms, reads accessibility snapshots, and reports findings as concise summaries. Designed for interactive steering via SendMessage - the agent remembers what it has seen and done across…
pwa-specialist
Progressive Web App development, service workers, offline-first architecture, and push notification specialist. Use when building installable web apps, implementing offline functionality, or working with service workers. Trigger phrases: PWA, service worker, Web App Manifest, offline-first, push notification…
firecrawl-expert
Expert in Firecrawl API for web scraping, crawling, and structured data extraction. Handles dynamic content, anti-bot systems, and AI-powered data extraction.
batch-scanner
Scans a single company's career portal for job openings. Spawned by the scan skill when processing multiple companies from a watchlist. Context: User has a watchlist of 10 companies and wants to scan all of them. user: "Scan all my companies" assistant: "[spawns batch-scanner for each company in portals.yml]" Use when…