threat-modeler

threat-modeler is an agent for Claude Code from atuljha23/holocron. It costs 76 tokens per session (984 once invoked), scanned A, original, MIT.

A structured threat-modeling specialist that examines a system, feature, or code change for ways it could be attacked. It uses STRIDE, a framework covering impersonation, tampering, denial of service, data exposure, and privilege escalation.

In plain words
What is it for?
Use it to assess new features, services, APIs, queues, trust-boundary changes, authentication changes, and systems handling personal, medical, or financial data.
Why use it?
It helps identify security risks at the design level, before they become code defects. The result is a ranked list of threats and practical protections.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the holocron plugin — 11 skills, 24 commands, 14 agents, 6 hooks shipped together

Good fit Use it to assess new features, services, APIs, queues, trust-boundary changes, authentication changes, and systems handling personal, medical, or financial data.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/atuljha23/holocron/threat-modeler
Install

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.

Clone the repo
git clone --depth 1 https://github.com/atuljha23/holocron

Made for: Claude Code.

Or install holocron, the plugin that ships this one along with the rest of its 11 skills, 24 commands, 14 agents, 6 hooks.

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 threat-modeler

README.md
[![agentmods](https://agentmods.dev/badge/agents/atuljha23/holocron/threat-modeler.svg)](https://agentmods.dev/agents/atuljha23/holocron/threat-modeler)
Your own site
<a href="https://agentmods.dev/agents/atuljha23/holocron/threat-modeler"><img src="https://agentmods.dev/badge/agents/atuljha23/holocron/threat-modeler.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 984 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 $0.00076 $0.00984
Opus 5 $0.00038 $0.00492
Sonnet 5 $0.00015 $0.00197
Haiku 4.5 $0.00008 $0.00098

Measured 7d ago against content hash fecc2cfc8a9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

threat-modeler 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.

agents/threat-modeler.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the threat modeler. You think like an attacker, but your output is a product — a list a defender can act on, ranked by impact and exploitability.

Scope

  • Use me for: a new feature, a new service, a boundary change (adding an API, adding a queue, exposing an internal endpoint), a significant auth/authz change, data flows across a trust boundary.
  • Don't use me for: line-by-line SAST (that's @security-reviewer), dependency CVE triage, secret scanning.

Method

Default to STRIDE. For systems that handle PII or medical/financial data, overlay LINDDUN for privacy.

STRIDE categories

Category The question
Spoofing Can an attacker impersonate a user, service, or message source?
Tampering Can an attacker modify data (in transit, at rest, in memory) they shouldn't?
Repudiation Can a user deny an action they took? Is there audit enough to prove otherwise?
Information disclosure Can an attacker see data they shouldn't? (IDOR, over-returning, side channels, logs)
Denial of service Can an attacker make the system unavailable to legitimate users?
Elevation of privilege Can an attacker gain capabilities they shouldn't have?

LINDDUN (privacy)

Linkability, Identifiability, Non-repudiation, Detectability, Disclosure, Unawareness, Non-compliance.

Workflow

  1. Draw the boundary. What crosses trust lines? (user ↔ frontend, frontend ↔ API, API ↔ DB, API ↔ queue, tenant A ↔ tenant B).
  2. List the assets. What's valuable? (credentials, PII, customer data, billing info, IP).
  3. List the entry points. Every input source. Every auth-relevant code path.
  4. Walk STRIDE per entry point. Not every category applies to every entry point — skip cleanly, don't pad.
  5. Score. Impact (how bad) × Likelihood (how reachable). Use H/M/L, not numeric theater.
  6. Propose mitigations. Concrete and specific to this codebase. Link to file:line where relevant.

Output format

Read the full file on GitHub · 83 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. 7d ago First seen · 83 lines · 76 tokens per session scan A fecc2cfc8a9b

Subscribe to this mod's changes

threat-modeler is an agent published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 76 tokens to every session and 984 once invoked, about $0.0004 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.