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 mattgierhart/PRD-driven-context-engineering --skill prd-v09-alternatives-pagesgit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWrote 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/mattgierhart/prd-driven-context-engineering/prd-v09-alternatives-pages)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v09-alternatives-pages"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v09-alternatives-pages/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/mattgierhart/prd-driven-context-engineering/prd-v09-alternatives-pages"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v09-alternatives-pages.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00106 | $0.02334 |
| Opus 5 | $0.00053 | $0.01167 |
| Sonnet 5 | $0.00021 | $0.00467 |
| Haiku 4.5 | $0.00011 | $0.00233 |
Grade A, and why
prd-v09-alternatives-pages 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alternatives Pages (Competitive Comparison SEO/CRO)
Position in workflow: v0.9 AEO Audit → v0.9 Alternatives Pages → v0.9 Launch Metrics
Execution Mode
Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.
| Mode | What this skill produces |
|---|---|
| quick | 2 pages for the single most-searched competitor (X-vs-us + alternative-to-X) |
| standard | 5–10 pages covering top 3–5 competitors with both variant types; CRO copy + comparison table |
| deep | Full competitor portfolio (10+ competitors); plus multi-way comparison ("X vs Y vs Z"); page-level A/B test plan; SEO targeting per page |
What This Does
Produces a portfolio of high-intent comparison pages — /x-vs-us and /alternative-to-x — that capture buyers actively searching for competitor names + comparison/alternative keywords. These are the highest-converting acquisition surface for B2B SaaS and many consumer products: the buyer has already passed awareness and is in active evaluation.
The pages must be fair, credible, and conversion-oriented — acknowledging where the competitor wins, claiming where you win, with social proof and a clear "when to pick each" guide. Aggressive trashing fails: buyers fact-check, and one false claim loses the page.
How It Works
- Source the competitor list — From the AEO Audit's comparison gaps and v0.2 CFD- competitive landscape. Rank by search volume (use Ahrefs/Semrush/free volume estimators) × buyer-intent strength.
- For each competitor, design two pages:
/<competitor>-vs-<us>— Symmetric comparison. Buyer is comparing both./alternative-to-<competitor>— Asymmetric. Buyer is leaving competitor or shopping replacements.
- Apply the page template (see Output Template) — Honest comparison table on 5–8 dimensions, "When to pick each" guidance, your unique attributes (from Dunford positioning), social proof, CTA.
- Anchor in positioning rules — Each page must respect the BR-POS-* constraints. If positioning says "not for enterprise procurement," the page does not court enterprise buyers.
- Plan attribution — Each page gets its own UTM source and a conversion event. Track per-page activation rate to identify dead pages.
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 · 192 lines · 106 tokens per session scan A af81962f7417
prd-v09-alternatives-pages is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 12d ago), licensed MIT. It adds 106 tokens to every session and 2,334 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…