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-reviewgit 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-review)<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/meta-review"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/meta-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/stefanoskarakasis/product-marketing-skills/meta-review"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/meta-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 | $0.00083 | $0.02008 |
| Opus 5.5 | $0.00033 | $0.00803 |
| Sonnet 5.5 | $0.00017 | $0.00402 |
| Haiku 4.5 | $0.00008 | $0.00201 |
Grade A, and why
meta-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 8d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
meta-review
Audits a skill's SKILL.md against SKILL-SPEC.md — the one standard every
skill in this repo is supposed to meet. Runs the same 18-point checklist
SKILL-SPEC.md Section 13 defines, returns a pass/fail per check, and
prioritizes fixes so the skill's author knows exactly what to do next.
This is a spec-compliance auditor, not a content-quality judge. It checks structure — is every required section present, does frontmatter have every required field, is the file under 500 lines — not whether the skill's actual domain logic is good. Judging domain logic requires domain expertise this skill doesn't have; a human or a domain-specific reviewer does that.
Trigger
-
When: A skill's
SKILL.mdneeds to be checked against the repo's authoring standard — before merging a new skill, after editing an existing one, or as a periodic health check. -
Not for: Checking the correctness of a skill's actual output (a GTM brief, a positioning statement, a retro summary) → use
meta-verify. Detecting cross-skill patterns or proposing guardrails → usemeta-synthesis. Extracting learnings from a single completed session → usemeta-learn. -
Example prompts:
- "Review the retro skill"
- "Audit pmm-okrs against spec"
- "Does stakeholder-maps meet the authoring standard?"
- "Check every skill in pmm-execution"
Inputs
- Args: Skill name (required) — the directory name of the skill to audit,
e.g.
retroorpositioning-messaging. If the user names a whole plugin instead of one skill, run this skill once per skill in that plugin and report all results together. - Defaults: N/A — a skill name is always required.
- Context keys:
SKILL-SPEC.md(the standard being enforced) and the target skill'sSKILL.mdfile. No brain context needed.
Pre-flight
- Load
SKILL-SPEC.mdfrom the repo root. If it's missing, stop — there's nothing to audit against. - Locate the named skill's
SKILL.md. If the skill directory doesn't exist, say so and ask for the correct name rather than guessing. - This skill is context-agnostic. Do not load
/foundation/brain.md.
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.
- 8d ago Changed · -1 lines · -21 tokens per session 8e0fc04036b5
- 16d ago Changed · +1 lines 34e365386755
- 17d ago Changed · +1 lines 33ffaa8f31f8
- 1mo ago First seen · 187 lines · 104 tokens per session scan A 48f9250da049
meta-review is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (8 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 2,008 once invoked, about $0.0003 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
code-review
Review code for actionable defects. Correctness is the core; performance and security are optional sub-cases of the same engine. Anchors on agreements between participants across a boundary, forces a violating execution, and refutes every candidate before reporting. Use when asked to review changes, find bugs, audit a…
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…
team-review
Review changed code for reuse, quality, and efficiency using a team of persistent named reviewers. This skill should be used when the user says "team review", "review with team", or wants parallel code review with persistent team members for follow-up questions. Similar to /subagent-review but reviewers persist after…
roslyn-query
Query .NET/C# codebases using Roslyn AST analysis via dotnet run file. Use for tracing data flow, auditing API usage, finding pattern violations, or ad-hoc codebase queries.
analyze-pr
Review PR for quality, security, and coverage (GitHub/GitLab/Forgejo).
review-pr
Review a Pull Request in one of two postures: an expository "tour guide" that walks through changes in logical order, or an adversarial audit that assumes the change is wrong until proven safe and hunts for the failure mode. Triggers: "review PR #123", "adversarial review", "walk me through this PR", "PR tour guide"…