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.
git clone --depth 1 https://github.com/threatcl/claude-pluginWrote 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/threatcl/claude-plugin/threat-review)<a href="https://agentmods.dev/commands/threatcl/claude-plugin/threat-review"><img src="https://agentmods.dev/badge/commands/threatcl/claude-plugin/threat-review.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 | $0.00012 | $0.00637 |
| Opus 5 | $0.00006 | $0.00318 |
| Sonnet 5 | $0.00002 | $0.00127 |
| Haiku 4.5 | $0.00001 | $0.00064 |
Grade A, and why
threat-review 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running a structured security review of the threat model identified by $ARGUMENTS. Gather data first, then synthesize. Be concrete — every finding must reference specific threats, controls, or policies you pulled, not generic security advice.
1. Load the model
Use the get_threat_model MCP tool (preferred) to fetch the model by slug or ID. Fall back to threatcl cloud view -model-id $ARGUMENTS if MCP is unavailable. Note: name, status, last-updated, threat count, control count.
2. Find unmitigated threats
Run the search MCP tool (or threatcl cloud search) scoped to this model with has-controls=false. List every threat with no mapped controls — these are the highest-priority gaps.
3. Tally STRIDE coverage
Across all threats in the model, count which STRIDE categories appear. Any category that's entirely absent is worth calling out, but only suggest adding threats in missing categories if they genuinely apply to the system being modeled.
4. Run policy evaluation
Run threatcl cloud policy evaluate -model-id <id>. Surface every error and warning verbatim — the policies are configured by the org and you shouldn't editorialize them away. If policy evaluation isn't available (no policies defined, MCP-only environment), say so and skip.
5. Cross-check the threat library
Use list_library_items (MCP) or threatcl cloud library threats to scan the org's threat library. Identify up to three library threats whose STRIDE/impacts/tags overlap with the model's domain but aren't yet referenced in it. Suggest each by ref ID and explain why it fits.
6. Output the report
Format:
# Review: <model name> (<slug>)
## Summary
<1–2 sentences: overall posture, biggest concern>
## Unmitigated threats (<count>)
- <threat name> — STRIDE: <category> — Impacts: <list>
…
## STRIDE coverage
- Spoofing: <covered count> threats
- Tampering: …
- (mark any absent categories explicitly)
## Policy evaluation
- Errors: <count> · Warnings: <count> · Info: <count>
- <severity>: <policy name> — <violation reason>
…
## Library suggestions
- T-<ref>: <name> — why this fits this model
…
## Recommended next actions
1. <concrete next step, e.g. "Add a control to threat 'X' mitigating Y">
…
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.
- 6d ago First seen · 64 lines · 12 tokens per session scan A 107fa91795a1
threat-review is a command published in the GitHub repository threatcl/claude-plugin (4 stars, last pushed 22d ago), licensed MIT. It adds 12 tokens to every session and 637 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.