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.
npx agentmods add commands/redhatproductsecurity/agentic-threat-modeling/threat-modelgit clone --depth 1 https://github.com/RedHatProductSecurity/agentic-threat-modelingWrote 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.
[](https://agentmods.dev/commands/redhatproductsecurity/agentic-threat-modeling/threat-model)<a href="https://agentmods.dev/commands/redhatproductsecurity/agentic-threat-modeling/threat-model"><img src="https://agentmods.dev/badge/commands/redhatproductsecurity/agentic-threat-modeling/threat-model.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.00676 |
| Opus 5 | $0.00010 | $0.00338 |
| Sonnet 5 | $0.00004 | $0.00135 |
| Haiku 4.5 | $0.00002 | $0.00068 |
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 5d 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.
What it actually says
Invoke the threat-model skill to generate a threat model.
Parse the user's arguments to determine:
Framework (optional — if not specified, recommend one):
stride— STRIDE (Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service, Elevation of Privilege)pasta— PASTA (Process for Attack Simulation and Threat Analysis)linddun— LINDDUN (privacy-focused threat modeling)vast— VAST (Visual, Agile, Simple Threat modeling)attack-trees— Attack Trees (goal-decomposition analysis)octave— OCTAVE (organizational risk assessment)
Mode (optional — default: guided):
quick— fast, non-interactive scan using STRIDEguided— interactive session with auto-discovery + interviewfull— comprehensive multi-framework analysispr— threat-model the current branch's diff against mainpr:123— threat-model a specific PR by numberupdate— refine an existing THREAT_MODEL.md with feedbackupdate "remove T-003, upgrade T-005 to Critical"— apply specific feedback inline
Actor personas (optional — default: auto-detect):
actors:insider— single actor focusactors:insider,supply-chain,apt— multiple actorsactors:all— all actor perspectives
External context (optional — for docs the code scan won't find: architecture write-ups, compliance assessments, prior threat models, SBOMs):
context:docs/ess_controls.md— a file path (relative to repo root)context:docs/— a directory (ingests all supported files)context:https://example.com/arch— a public URL (authenticated pages require exporting first)- Comma-separated for multiple:
context:docs/ess_controls.md,docs/sar_report.md
Target (optional — default: current repository):
- A file or directory path to focus on
Always-on features (required in every mode — quick, guided, full):
- Code citations: every threat must include
file:linereferences grounding findings in the codebase. For absence-of-control threats, note where the control should exist. - Data classification table: Section 5.5 maps data types to sensitivity, storage, flows, and regulatory scope. Use this table to calibrate threat severity.
Examples:
/threat-model context:docs/openapi.yaml— ingest API spec before analysis/threat-model stride context:https://docs.google.com/doc/d/... context:sbom.json— STRIDE with external arch doc and SBOM
Arguments from user: $ARGUMENTS
If no arguments provided, start an interactive guided session. Ask the user to choose framework, external context, and scope BEFORE scanning the codebase — don't start analysis until they've made their selections.
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.
- 5d ago First seen · 52 lines · 21 tokens per session scan A 6fa059e67ae8
threat-model is a command published in the GitHub repository RedHatProductSecurity/agentic-threat-modeling (4 stars, last pushed 25d ago), licensed Apache-2.0. It adds 21 tokens to every session and 676 once invoked, about $0.0001 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.