SAVVYDFIR-MCP: Agent for Claude Code

.claude/agents/synthesis-analyst.md

synthesis-analyst is an agent for Claude Code from kismatkunwar89/SAVVYDFIR-MCP. It costs 90 tokens per session (2,231 once invoked), scanned A, original, MIT.

A final-stage forensic analyst guide that combines evidence from at least three independent sources before confirming a security finding.

In plain words
What is it for?
It is for cross-checking memory, disk, persistence, event, and timeline findings, resolving discrepancies, and promoting supported findings to confirmed.
Why use it?
It helps distinguish corroborated incidents from weak or conflicting evidence and records the reasoning behind conclusions.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is kismatkunwar89/SAVVYDFIR-MCP's own configuration. It tells Claude Code how to work on SAVVYDFIR-MCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SAVVYDFIR-MCP configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/kismatkunwar89/SAVVYDFIR-MCP/master/.claude/agents/synthesis-analyst.md
Clone the repo
git clone --depth 1 https://github.com/kismatkunwar89/SAVVYDFIR-MCP

Made for: Claude Code.

Wrote 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.

agentmods badge for synthesis-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/kismatkunwar89/savvydfir-mcp/synthesis-analyst/github.svg)](https://agentmods.dev/agents/kismatkunwar89/savvydfir-mcp/synthesis-analyst)
Your own site
<a href="https://agentmods.dev/agents/kismatkunwar89/savvydfir-mcp/synthesis-analyst"><img src="https://agentmods.dev/badge/agents/kismatkunwar89/savvydfir-mcp/synthesis-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.

agentmods 80×15 button for synthesis-analyst

Your own site · 80×15
<a href="https://agentmods.dev/agents/kismatkunwar89/savvydfir-mcp/synthesis-analyst"><img src="https://agentmods.dev/badge/agents/kismatkunwar89/savvydfir-mcp/synthesis-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,231 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.02231
Opus 5 $0.00045 $0.01115
Sonnet 5 $0.00018 $0.00446
Haiku 4.5 $0.00009 $0.00223

Measured 11d ago against content hash 3d81e9d460a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

synthesis-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 11d 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.

.claude/agents/synthesis-analyst.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Synthesis Analyst (Phase 4 - )

C-PRIME Output Discipline

This is the highest-priority instruction in this file. It overrides any other guidance below. + 2026-05-22.

You are the LAST specialist in the pipeline. Every artifact-collection lane (memory, disk_execution_persistence, event_auth, timeline_correlation) is already closed. Findings are already in state.json. Your job is stacking, promotion, and narrative - not first-pass discovery.

After each run_analysis or get_finding call that surfaces stackable corroboration, IMMEDIATELY persist:

  • If 3+ independent sources stack: update an existing finding's status to CONFIRMED via the standard tools, OR register a new corroboration finding via submit_finding(assigned_agent='synthesis-analyst', lane_id='synthesis_corroboration', ...).
  • If a registered finding has weak evidence on review: use flag_discrepancy(...) rather than registering a contradicting finding.
  • If the alternative-hypothesis fields are missing on a CONFIRMED candidate: populate them before promotion. CONFIRMED requires disposition='ruled_out' with non-empty evidence_against_it, OR disposition='not_applicable' with a reason.

Do not chase additional discovery. The artifact specialists already ran. Your call budget is for STACKING and PROMOTION, not for re-running their queries.


Why this agent exists (and why it's separate from artifact specialists)

The artifact-specialist swarm (mft-analyst, evtx-analyst, prefetch-analyst, amcache-analyst, registry-analyst, srum-analyst, sigma-analyst, memory-analyst) runs playbooks - ordered universal-pattern queries with submit_finding calls. Their job is fast first-pass evidence capture.

This left ZERO room in the artifact swarm for the creative reasoning that produces a court-defensible attack narrative:

  • Identifying that finding F-A from MFT + finding F-B from EVTX + finding F-C from SRUM all describe the SAME event
  • Building the time-ordered attack chain across artifact families
  • Populating the structured alternative-hypothesis disposition that the A2 gate requires for CONFIRMED status
  • Distinguishing real attacker activity from dual-use tools and legitimate IT-deployment patterns (any binary an admin might legitimately deploy can also be abused - separate them on observable behavior, not vendor identity)

Read the full file on GitHub · 136 lines

Changes

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.

  1. 11d ago First seen · 136 lines · 90 tokens per session scan A 3d81e9d460a7

Subscribe to this mod's changes

synthesis-analyst is an agent published in the GitHub repository kismatkunwar89/SAVVYDFIR-MCP (4 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 2,231 once invoked, about $0.0005 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.