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 kkanakas/AI-Prompts-for-Product-Management --skill value-spec-analyzergit clone --depth 1 https://github.com/kkanakas/AI-Prompts-for-Product-ManagementWrote 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/kkanakas/ai-prompts-for-product-management/value-spec-analyzer)<a href="https://agentmods.dev/skills/kkanakas/ai-prompts-for-product-management/value-spec-analyzer"><img src="https://agentmods.dev/badge/skills/kkanakas/ai-prompts-for-product-management/value-spec-analyzer/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/kkanakas/ai-prompts-for-product-management/value-spec-analyzer"><img src="https://agentmods.dev/badge/skills/kkanakas/ai-prompts-for-product-management/value-spec-analyzer.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 | $0.00235 | $0.02936 |
| Opus 5 | $0.00118 | $0.01468 |
| Sonnet 5 | $0.00047 | $0.00587 |
| Haiku 4.5 | $0.00023 | $0.00294 |
Grade A, and why
value-spec-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 12d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Value Spec Review
A Chief Product Officer's review of a product specification. The goal is to surface strategic issues — value framing, capability gaps, second-order consequences — that engineering-led specs typically under-address. The output is direct, decision-oriented, and ends in an approve / don't-approve / approve-with-changes recommendation.
The lens
This is a value spec review, not a feature spec review. The reviewer reads the document as a CPO would: looking for whether the investment is defensible, whether the customer problem is real and quantified, whether the capability set is coherent, and whether the second-order effects (positive and negative) have been priced in. Engineering rigor in the document is noted but not the primary scoring axis.
Engineering-led specs tend to be strong on what and how, weak on why for the customer and what happens next. This skill leans into those weak spots deliberately.
When this fires
- Explicit invocation — "review this spec", "give me a CPO review", "/specreview", "/valuespec", "/cporeview", "analyze this value spec".
- Implicit invocation — user shares a Notion link, Google Doc, file upload, or pasted spec text and asks for review, critique, feedback, pressure-test, or "what do you think". When the artifact is clearly a product spec and the ask is evaluative, run this skill.
If the user invokes the skill without a spec attached, ask for it before proceeding. Do not improvise a generic answer.
Input gathering
If the user has not yet provided a spec, ask:
Which spec would you like me to review? Paste the content, share a Notion or Google Doc URL, or upload a file. If it has companion docs (PRD, URD, related implementation packs), point me at those too — second-order analysis is sharper when the surrounding product context is visible.
If the user provides only a Notion link, fetch it via the Notion connector. If they provide a Google Doc, fetch via the Drive connector. If a file is uploaded, read it directly. If they paste content inline, work from that.
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.
- 12d ago First seen · 145 lines · 235 tokens per session scan A 8721d71f444d
value-spec-review is a skill published in the GitHub repository kkanakas/AI-Prompts-for-Product-Management (3 stars, last pushed 3mo ago), licensed MIT. It adds 235 tokens to every session and 2,936 once invoked, about $0.0012 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 skills, from other repositories
memory-audit
An entry point for reviewing and maintaining an AI agent's stored memories. It describes how to remove repetition, preserve useful reasoning, and update memories when old conclusions no longer fit.
memory-audit-belief-duel
A guided review process for conflicting beliefs or memories. It examines cases where two conclusions cannot both be true, including conflicts between a general rule and a more specific memory.
memory-audit-discoverability
A review guide for checking whether stored memories can be found at the right time. It focuses on where memories are attached, when they are triggered, whether aliases are missing, and whether a parent has too many children.
memory-audit-pattern-extraction
A method for investigating repeated mistakes by comparing related memories and checking whether an earlier reminder failed. It looks at where the reminder was stored, when it was created, and whether it was strong enough to prevent the mistake.
memory-audit-node-decomposition
A method for splitting an oversized knowledge note into smaller notes, each focused on one independent idea. It also explains how to keep useful core information in the original note.
memory-audit-dead-data-purge
A review process for identifying memories that do not change future actions. It tests whether a note contains useful, experience-based guidance or only sounds meaningful without affecting decisions.