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 skills add baobao2333/prd-agent-kit --skill prd-08-risk-debt-reviewgit clone --depth 1 https://github.com/baobao2333/prd-agent-kitWrote 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/skills/baobao2333/prd-agent-kit/prd-08-risk-debt-review)<a href="https://agentmods.dev/skills/baobao2333/prd-agent-kit/prd-08-risk-debt-review"><img src="https://agentmods.dev/badge/skills/baobao2333/prd-agent-kit/prd-08-risk-debt-review/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.
<a href="https://agentmods.dev/skills/baobao2333/prd-agent-kit/prd-08-risk-debt-review"><img src="https://agentmods.dev/badge/skills/baobao2333/prd-agent-kit/prd-08-risk-debt-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00062 | $0.00948 |
| Opus 5.5 | $0.00025 | $0.00379 |
| Sonnet 5.5 | $0.00012 | $0.00190 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
prd-08-risk-debt-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 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Risk & Debt Review
Purpose
Expose the risks that AI-written PRDs usually hide: historical debt, unclear ownership, old behavior, compatibility, abuse, cost, operations burden, and responsibility transfer.
Inputs
- All previous PRD artifacts.
- Known system history, if available.
- Known legal, finance, risk-control, or operations constraints, if available.
Review principles
- Do not assume old systems are clean.
- Do not assume existing data can support new logic.
- Do not assume old clients behave correctly.
- Do not move product decisions to engineering by using vague wording.
- Do not hide business risk behind “optimize later”.
- Every high-risk item must have an owner or an explicit decision gap.
- Run a confidence loop before finalizing the review: ask whether the strategy is factually strong enough to defend. If not, find all known loopholes, propose fixes, loop back to the owning artifact, and repeat until no delivery-blocking loopholes remain. Do not finish with a list of blockers unless the missing item truly requires user or stakeholder input.
Process
- Review scope creep.
- Review undefined rules.
- Review compatibility and historical data.
- Review abuse and cost risk.
- Review operations burden.
- Review responsibility boundaries.
- Review legal / finance / risk-control dependency if relevant.
- Run the confidence loop: list loopholes, propose fixes, re-check the revised strategy, and preserve any remaining uncertainty.
- Recommend delete, simplify, confirm, keep, or loop back to an earlier stage.
Loop-back rules
- If the risk depends on product scope or version boundary, return to
prd-02-business-boundary. - If the risk depends on missing conditions, thresholds, states, permissions, or conflict handling, return to
prd-03-rule-modeler. - If the risk depends on unclear user/system behavior, return to
prd-04-flow-modeler. - If the risk depends on missing user-visible states or copy, return to
prd-05-page-interaction. - If the risk is caused by speculative controls or missing operations ownership, return to
prd-06-admin-config. - If the risk depends on vague metrics, alert triggers, logging, attribution, or QA evidence, return to
prd-07-data-acceptance. - Use
prd-09-prd-compressoronly when blocking items are resolved. - If a blocking item cannot be resolved from existing evidence with high confidence, ask the user for the specific missing decision, then continue after the answer.
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 · 96 lines · 62 tokens per session scan A f3005c173162
prd-08-risk-debt-review is a skill published in the GitHub repository baobao2333/prd-agent-kit (5 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 948 once invoked, about $0.0002 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.
Other skills, from other repositories
fto-triage
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
terms-of-service
Draft terms of service and a companion privacy notice matched to the product's form and feature modules, not legal advice, delivered as a Word document.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
ai-risk-management
Apply the NIST AI Risk Management Framework (AI RMF 1.0) and adjacent guidance to AI / ML systems — model lifecycle governance, fairness and bias evaluation, robustness, transparency, accountability, third-party model risk, monitoring for drift, and AI incident response. Broader than prompt-injection (which is the…