Claude Code

Everything this one agent is and does — and what to do about it.

Bottom line

Claude Code is Standard (100/100): no deductions. Credential risk Lower — revocable OAuth, enterprise-backed. Governed.

Anthropic · cli · pid:865:claude-code

Identity & Access

user: mark
email: mark@qpoint.io
org_id: org_qpoint
account_uuid: acct_7f3a91c4e0b2
host: mp-mbp
auth_method: oauth_jwt
cred_risk: Lowerrevocable OAuth, enterprise-backed

Process & Runtime

name / version: Claude Code · v2.1.161
configured_model: claude-opus-4-8
runtime_model: claude-opus-4-8
binary_path: /Users/mark/.local/bin/claude
cwd: /Users/mark/web/qpoint/bob-wire
config_source: /Users/mark/.claude/settings.json
kind: cli
first_seen: 2026-05-08T09:14:00Z
last_active: 2026-06-03T14:02:11Z

Data Access

data-risk 12 · MCP footprint 248

320

file reads

file writes

410

file opens

1.2k

tool calls

Sensitive paths

PathCategorySeverityOpens

./.envsecret_filehigh3

~/.aws/credentialscloud_credentialshigh1

MCP Servers

footprint 248 · 2 × 124 calls

ServerCalls

mcp.figma.com84

github-mcp40

Token & Cost

6.9M tokens

input

1.2M

output

180.0k

cache read

4.8M

cache write

600.0k

reasoning

90.0k

total cost$214.50

By model

claude-opus-4-86.9M tok · 1.2k calls · $214.50

Security Score

100

Standard

score / 100 · target ≥ 80

Why this score:no deductions — clean posture.

no prior regression

Risk factors

No risk factors.

Network Egress

detail-level signal

Host : PortTLSAllowlisted

api.anthropic.com:443TLSv1_3yes

mcp.figma.com:443TLSv1_3no

Derived: deductions (factors × FACTOR_PTS) · delta vs worst_score · data-risk sub-score (severity-weighted opens) · MCP footprint (servers × calls) · isCompoundRisk — from app/data/c16-fleet.ts (qcontrol /api shape).