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 yarlson/yarstack --skill marketing-claims-reviewgit clone --depth 1 https://github.com/yarlson/yarstackWrote 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/yarlson/yarstack/marketing-claims-review)<a href="https://agentmods.dev/skills/yarlson/yarstack/marketing-claims-review"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/marketing-claims-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/yarlson/yarstack/marketing-claims-review"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/marketing-claims-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 | $0.00043 | $0.00336 |
| Opus 5 | $0.00022 | $0.00168 |
| Sonnet 5 | $0.00009 | $0.00067 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
marketing-claims-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.
What it actually says
Marketing Claims Review
Own claim substantiation, positioning, comparisons, and first-visitor clarity regardless of file location.
Workflow
- Confirm pages, audience, and audit-only or authorized rewrite mode.
- Build a capability map with implementation and runtime evidence taking precedence over marketing prose, demos, and roadmap material.
- Classify material claims as
accurate,unclear,unsupported,exaggerated,stale, orfalse. - Test whether a first-time visitor can identify the product, intended user, problem, mechanism, difference, limitations, and next action.
- For each problematic claim, cite evidence and recommend
keep,rewrite,move,remove,qualify, orprove. - Rewrite only when authorized, preserving distinctions between shipped, partial, experimental, planned, and unsupported behavior.
- After an authorized rewrite, use
text-improveto improve the prose without weakening substantiation, necessary qualifications, or intentional voice.
Use docs-review for repository-document structure and discoverability, and docs-drift-review only for drift caused by the current change. Comparative claims requiring external competitor evidence remain unverified unless authoritative evidence is available and its use is authorized.
Do not infer capabilities from aspirations, invent proof, or force parallel agents.
Finish with scoped claims, evidence, dispositions, authorized edits, and unresolved proof needs.
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 · 25 lines · 43 tokens per session scan A 607cfda08dcc
marketing-claims-review is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 336 once invoked, about $0.0002 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
capture
Capture an engineering decision into Hunch's graph via a grilling interview (topic, rationale, rejected alternatives).
heal
Reconcile docs/code with Hunch's decision graph (doc≠graph drift), never rewriting prose silently.
fix
Fix a bug grounded in Hunch (past root causes, constraints, blast radius).
fragile
Report the most fragile parts of this codebase, with evidence from Hunch.
why
Explain why a file or symbol is the way it is, from Hunch's decision graph.
k-review
An independent review of frozen Git base and head versions, checking both the written specification and project standards.