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 stefanoskarakasis/Product-Marketing-Skills --skill meta-verifygit clone --depth 1 https://github.com/stefanoskarakasis/Product-Marketing-SkillsWrote 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/stefanoskarakasis/product-marketing-skills/meta-verify)<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/meta-verify"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/meta-verify/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/stefanoskarakasis/product-marketing-skills/meta-verify"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/meta-verify.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 | $0.00092 | $0.01577 |
| Opus 5 | $0.00046 | $0.00788 |
| Sonnet 5 | $0.00018 | $0.00315 |
| Haiku 4.5 | $0.00009 | $0.00158 |
Grade A, and why
meta-verify 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
meta-verify
A second pair of eyes on a skill's output, applying the exact standard the
originating skill already committed to — its own ## Quality Gate table and
## Operating Rules. Catches what the first pass missed, especially when
the same session that produced the output is also the one that's about to
mark it done.
This isn't a second opinion using a different, invented rubric — it's a
faithful re-application of the standard that skill already declared for
itself. If a skill's own Quality Gate is weak, that's a meta-review
finding against that skill's SKILL.md, not something this skill
compensates for by inventing its own scoring.
Trigger
-
When: A skill has produced output and it's about to be delivered externally (sent to sales, shared with leadership, published) — a second pass before it leaves the building.
-
Not for: Auditing a
SKILL.md's own structure → usemeta-review. Extracting learnings from a completed session → usemeta-learn. Detecting patterns across sessions → usemeta-synthesis. -
Example prompts:
- "Check this positioning brief before I send it"
- "Verify the last GTM strategy output"
- "Did this retro actually pass its own quality gate?"
- "Second-pass this before it goes to leadership"
Inputs
- Args: The output to verify, and which skill produced it.
n.v.t.if invoked immediately after that skill's own session — infer both from context. - Defaults: If the originating skill isn't obvious from the output itself, ask.
- Context keys: The originating skill's own
SKILL.md— specifically its## Quality Gateand## Operating Rulessections. No brain context needed beyond what the originating skill itself required.
Pre-flight
- Load the originating skill's
SKILL.md. If it doesn't exist or doesn't declarequality_gate: true, say so — there's no standard to re-check against, and this skill isn't the place to invent one on the spot. - This skill is context-agnostic. It applies the originating skill's own
declared standard; it does not load
/foundation/brain.mdindependently.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 169 lines · 92 tokens per session scan A d01641b2a5be
meta-verify is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (5 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 1,577 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 2026-08-31.
Other skills, from other repositories
eval-suite-design
Use this skill when the user asks to "design an eval suite", "build evals for my AI feature", "create an evaluation framework", "how do I evaluate my AI", "what evals should I run", "build an eval system", or wants to create a systematic evaluation framework for an AI-powered product feature. Typically run after…
regression-testing
Use this skill when the user asks to "prevent regressions in AI quality", "regression testing for AI", "how do I know if a prompt change broke something", "before/after evaluation for model changes", "catch quality regressions", or wants to set up a process that catches when a model update, prompt change, or system…
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
intended-vs-implemented
The method for finding the gap between what a system is supposed to do and what the code actually does — the class of bug generic scanners miss because they have no model of intent. Defines what counts as documented intent, what counts as implementation evidence, which mismatches matter, and how to avoid hand-wavy…
test-scenarios
Create comprehensive test scenarios from user stories with test objectives, starting conditions, user roles, step-by-step actions, and expected outcomes. Use when writing QA test cases, creating test plans, defining acceptance tests, or preparing for feature validation.
becoming-senior-pm
Use this skill when the user asks "how do I become a senior PM", "what does senior PM actually mean", "I want to get promoted to senior", "what's the difference between PM and senior PM", "I've been a PM for 2–3 years and want to grow", "my manager says I need to work more strategically", "I'm stuck at PM level", or…