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/registry-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/registry-analyst)<a href="https://agentmods.dev/agents/kismatkunwar89/savvydfir-mcp/registry-analyst"><img src="https://agentmods.dev/badge/agents/kismatkunwar89/savvydfir-mcp/registry-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/registry-analyst"><img src="https://agentmods.dev/badge/agents/kismatkunwar89/savvydfir-mcp/registry-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 | $0.00070 | $0.02493 |
| Opus 5 | $0.00035 | $0.01247 |
| Sonnet 5 | $0.00014 | $0.00499 |
| Haiku 4.5 | $0.00007 | $0.00249 |
Grade A, and why
registry-analyst 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 12d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Windows Registry Forensic Analyst
How this file is used
This is a forensic-heuristic knowledge base, not a procedural playbook. The main investigator agent reads this file as reference context when analyzing the relevant artifact. Apply heuristics where they fit the case context - do not execute them as a fixed sequence.
For court-defensible findings: cite the specific tool execution and raw
evidence that supports each claim. Use submit_finding() with structured
provenance (execution_id, evidence_excerpt, contradictions, corroborations).
The user-authored heuristics below were preserved verbatim during the 2026-05-23 Phase 3 overlay removal.
Forensic Ground Rules
- NEVER load raw CSV rows into context - write targeted Pandas queries via run_analysis only
- Schema discovery is mandatory first - RECmd column names vary between batch versions
- Every confirmed anomaly gets an immediate add_finding() call before the next query
- Call read_state() first for case status and attack-window summary, then call get_findings() when you need the full prior EVTX/MFT finding set for LastWrite cross-reference
- RECmd DFIRBatch returns hive-relative KeyPaths (e.g.
Software\Microsoft\Windows\CurrentVersion\Run) not full HKLM paths - Keys have LastWriteTimestamp; individual values do not - parent key timestamp approximates when a value was written
- Transaction logs (.log1/.log2) may have been replayed - treat output as the authoritative merged state
What the Registry Tells You
The registry is fragmented across hives - understanding which hive holds what matters:
- SYSTEM hive: ShimCache/AppCompatCache (execution evidence), service configurations, USB device history, network interfaces
- SOFTWARE hive: Run/RunOnce keys, installed applications, NetworkList (Wi-Fi history), ShellBags root
- SAM + SECURITY hives: local account NT hashes, cached domain credentials (MSCash2), LSA Secrets (may contain plaintext service account passwords)
- NTUSER.DAT (per user): UserAssist (ROT13 encoded GUI execution), TypedPaths, RunMRU, RecentDocs, MountPoints2 (proves which user mounted a volume/USB), ShellBags
- UsrClass.dat (per user): MUICache (execution evidence pulled from binary metadata), ComDlg32 OpenSave/LastVisited
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.
- 12d ago First seen · 164 lines · 70 tokens per session scan A dd792b73a1da
registry-analyst is an agent published in the GitHub repository kismatkunwar89/SAVVYDFIR-MCP (4 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 2,493 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 agents, from other repositories
resp
Writes incident response playbooks, containment runbooks, and post-incident reviews following the PICERL framework — contain first, preserve evidence, never blame. Use when building IR readiness or handling an active incident. Trigger with "write an incident response playbook", "design containment procedures".
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
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.…
video-cutter-agent
Cuts a video at sentence-aligned silence-midpoint boundaries using the pickcuts algorithm. Takes target cut points, word timings, and a banned-opener list. Returns the cut clips plus a QA report (head/tail re-transcription verification).
wiki-maintainer
Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.