threat-model

threat-model is a skill for Claude Code from ruvnet/metaharness. It costs 0 tokens per session (664 once invoked), scanned A, original, MIT.

A security report for an MCP-enabled harness showing which tools and permissions are allowed or denied. MCP is a way for an agent to connect to external tools.

In plain words
What is it for?
Use it during pull-request or compliance review to produce a clean, medium, or high-risk verdict for a scaffolded harness.
Why use it?
It gives reviewers a compact view of dangerous permissions, access to secrets, network or shell access, file writing, and audit logging.

Skill for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: reads .claude/ paths; mentions Codex.

Part of the agent-harness-generator plugin — 14 skills, 1 plugin shipped together

Good fit Use it during pull-request or compliance review to produce a clean, medium, or high-risk verdict for a scaffolded harness.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ruvnet/metaharness/threat-model
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.

Any agent
npx skills add ruvnet/metaharness --skill threat-model
Clone the repo
git clone --depth 1 https://github.com/ruvnet/metaharness

Made for: Claude Code.

Or install agent-harness-generator, the plugin that ships this one along with the rest of its 14 skills, 1 plugin.

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-model

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruvnet/metaharness/threat-model.svg)](https://agentmods.dev/skills/ruvnet/metaharness/threat-model)
Your own site
<a href="https://agentmods.dev/skills/ruvnet/metaharness/threat-model"><img src="https://agentmods.dev/badge/skills/ruvnet/metaharness/threat-model.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 664 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00000 $0.00664
Opus 5 $0.00000 $0.00332
Sonnet 5 $0.00000 $0.00133
Haiku 4.5 $0.00000 $0.00066

Measured 8d ago against content hash 2106856f0f27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

threat-model 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 8d 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-plugin/skills/threat-model/SKILL.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.

threat-model

Codex skill: MCP threat-model artifact for PR / compliance review (iter 112 → iter 114). User-labelled "enterprise gold."

What it does

Renders the existing mcp-scan findings as a clean threat-model artifact in the shape a security / compliance reviewer wants to see attached to a PR:

MCP Threat Model

  Allowed tools:         3
  Denied tools:          14
  Dangerous permissions: 0
  Secrets reachable:     no
  Network access:        no
  Shell access:          no
  File write:            no
  Default-deny policy:   yes
  Audit log:             yes

Verdict: clean (exit 0)

Same underlying scan as mcp-scan, presented as a single-screen artifact.

Verdict Exit Triggers
clean 0 no dangerous perms, no secret exposure
medium 1 network OR file-write granted, OR no audit log
high 2 shell granted OR default-deny OFF OR secrets reachable

The "secrets reachable" heuristic is conservative: true when MCP is in use AND deny rules don't guard .env* AND allow rules include any Read(...) grant.

Usage from Codex

/threat-model path=./my-harness
/threat-model path=./my-harness bundle=true

Equivalent CLI

harness threat-model ./my-harness                # text artifact
harness threat-model ./my-harness --json         # full envelope
harness threat-model ./my-harness --bundle       # ADR-031 schema-1
harness threat-model ./my-harness --out tm.json  # write to file

When to attach this to a PR

  • Adding a new MCP server / tool
  • Loosening a permission allow rule
  • Pulling in a new dependency that exposes shell/network capabilities
  • Any change to .harness/mcp-policy.json or .claude/settings.json permissions

The artifact is small enough to paste verbatim into the PR description.

  • validate-harness (iter 22) — release-readiness umbrella (includes mcp-scan)
  • score-harness (iter 114) — broader 0-100 scorecard; MCP safety is one of its 5 dimensions
  • repo-genome (iter 114) — pre-scaffold readiness; MCP risk is one of its 7 sections

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. 8d ago First seen · 83 lines · 0 tokens per session scan A 2106856f0f27

Subscribe to this mod's changes

threat-model is a skill published in the GitHub repository ruvnet/metaharness (633 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 664 tokens. 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 2026-08-30.