threat-model

Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model, or the user explicitly asks to create, update, or persist a repository threat model. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable instruction skill with clear sequencing, validation checkpoints, and proper progressive disclosure to a real bundle reference. Its only weakness is conciseness: the repository-scope / not-diff-findings guidance is restated many times across sections where a single authoritative statement would suffice.

Suggestions

Consolidate the repeated 'stay at repository scope, do not center on the current diff/touched subsystem' guidance — stated in the Objective, Workflow step 6, and Hard Rules (lines 53-58) — into a single Hard Rule, removing the duplicates.

Merge the closely related Hard Rules about vulnerability-class scope (line 58) and not turning the phase into diff findings (line 54) into one rule to reduce token redundancy.

Trim Workflow step 6's three sub-bullets once the repository-scope rule is stated once elsewhere, keeping only the verification intent ('sanity-check the model is repository-scoped and covers surfaces before narrow examples').

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no conceptual throat-clearing about what threat modeling is), but the 'stay at repository scope / not about the current diff' guidance is repeated across the Objective, Workflow step 6, and four separate Hard Rules, which could be tightened into one statement.	2 / 3
Actionability	Gives concrete, executable instruction — specific file paths to read ('../../references/security-guidance.md', 'references/threat-model-guidance.md'), a precise cache-match rule on 'Repository' and 'Version' lines, and an explicit append-and-write step — which is actionable without code per the instruction-skill scoring note.	3 / 3
Workflow Clarity	The 7-step Workflow is clearly sequenced with explicit checkpoints: a cache-match gate in step 2, a 'stop and ask the user' guard in Artifact Resolution, and a sanity-check checklist in step 6 before finalizing, satisfying the validation-checkpoint anchor.	3 / 3
Progressive Disclosure	SKILL.md is a lean overview that defers the detailed generation checklist to the verified one-level-deep reference 'references/threat-model-guidance.md', with references clearly signaled and content appropriately split rather than inlined.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concise description that clearly defines the skill's niche, what it does, and when to trigger it, while explicitly excluding adjacent scan types to avoid misfires. It is not above 3 because there is no higher anchor; it is well above 2 given the explicit triggers and concrete actions.

Dimension	Reasoning	Score
Specificity	Names concrete actions — 'create, update, or persist a repository threat model' — matching the anchor for listing multiple specific concrete actions, rather than vague phrasing.	3 / 3
Completeness	Explicitly states what it does (create/update/persist a repository threat model) and when to use it via a clear 'Use when...' clause with multiple explicit triggers.	3 / 3
Trigger Term Quality	Includes natural terms a user would say ('threat model', 'threat-modeling phase', '$threat-model') with good coverage and a clear negative-trigger boundary.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (threat-modeling phase of a security scan) with distinct triggers and an explicit 'Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans' exclusion that lowers conflict risk.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/codex-security/skills/threat-model/SKILL.md
Commit: 11c74d6

Reviewed: 17 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.