What is threat-model-feedback?

A feedback collector for a completed threat model that records the user's answers in a GitHub issue. GitHub issues are shared project tickets for reporting problems, requests, and follow-up work.

Use it after reviewing a threat model to record its usefulness, missing or incorrect content, false alarms, quality rating, and additional comments.

It gathers structured feedback instead of leaving comments or quality concerns unrecorded. The result gives the team a trackable place to improve the report.

threat-model-feedback — Command by RedHatProductSecurity

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/RedHatProductSecurity/agentic-threat-modeling

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/redhatproductsecurity/agentic-threat-modeling/threat-model-feedback/github.svg)](https://agentmods.dev/commands/redhatproductsecurity/agentic-threat-modeling/threat-model-feedback)

Your own site

<a href="https://agentmods.dev/commands/redhatproductsecurity/agentic-threat-modeling/threat-model-feedback"><img src="https://agentmods.dev/badge/commands/redhatproductsecurity/agentic-threat-modeling/threat-model-feedback/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/redhatproductsecurity/agentic-threat-modeling/threat-model-feedback"><img src="https://agentmods.dev/badge/commands/redhatproductsecurity/agentic-threat-modeling/threat-model-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 715 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.

Model	Per session	Once invoked
Fable 5.1	$0.00014	$0.00715
Opus 5.5	$0.00006	$0.00286
Sonnet 5.5	$0.00003	$0.00143
Haiku 4.5	$0.00001	$0.00072

Measured 2mo ago against content hash cd8b47a72b07, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

threat-model-feedback 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 2mo 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.

module/commands/threat-model-feedback.md · 71 lines

What it actually says

Collect feedback about the most recent threat model and file it as a GitHub issue using the Feedback issue template.

Ask the user these questions one at a time:

How useful was this threat model? Options: Very useful / Somewhat useful / Not useful
Which section was most valuable? Options: Executive summary / Architecture overview / Threats / Attack scenarios / Mitigations / Data classification / Other
Was anything missing or wrong? (free text, or "nothing")
Were there any false positives — threats that don't actually apply? (free text, or "none")
On a scale of 1-5, how would you rate the overall quality? (1 = poor, 5 = excellent)
Would you use this tool again? Options: Yes / Maybe / No
Any additional comments? (free text, or skip)

Filing the Issue

After collecting answers, try these in order — a filed issue is more useful than a link the user might not click, so only fall back to a link if neither tool is available.

1. GitHub CLI (gh), if installed and authenticated: Check with gh auth status. If authenticated, create the issue directly:

gh issue create \
  --repo RedHatProductSecurity/agentic-threat-modeling \
  --title "[Feedback] <one-line summary from the usefulness + rating answers>" \
  --label feedback \
  --body "$(cat <<'EOF'
**How useful was this threat model?** {usefulness}

**Which section was most valuable?** {most_valuable}

**Was anything missing or wrong?** {missing}

**Were there any false positives?** {false_positives}

**Overall quality rating (1-5):** {rating}

**Would you use this tool again?** {use_again}

**Additional comments:** {comments}
EOF
)"

Share the issue URL that gh issue create returns.

2. A connected GitHub MCP server, if gh isn't installed or isn't authenticated: If an MCP tool for creating GitHub issues is available in this session, use it against the same repository (RedHatProductSecurity/agentic-threat-modeling) with the same title, labels, and body as above.

3. Fallback: a pre-filled link, if neither of the above is available: Construct a pre-filled "new issue" URL against the Feedback issue form, URL-encoding each answer into its field:

https://github.com/RedHatProductSecurity/agentic-threat-modeling/issues/new?template=feedback.yml&title=%5BFeedback%5D&usefulness={usefulness}&most-valuable={most_valuable}&missing={missing}&false-positives={false_positives}&rating={rating}&use-again={use_again}&comments={comments}

Present it as:

Thanks for the feedback! Click here to file it: Submit Feedback

The issue will open pre-filled with your answers on GitHub. Just review and click "Submit new issue."

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.

2mo ago First seen · 71 lines · 14 tokens per session scan A cd8b47a72b07

Subscribe to this mod's changes

threat-model-feedback is a command published in the GitHub repository RedHatProductSecurity/agentic-threat-modeling (14 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 715 once invoked, about $0.0001 per session on Opus 5.5. 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.