narrative-review

narrative-review is a skill for Claude Code, Codex from Waddling-Penguin/mogkit. It costs 4 tokens per session (1,143 once invoked), scanned A, original, MIT.

A critical review of a strategy document, six-pager, or memo from the viewpoint of a skeptical executive. It finds gaps in the reasoning, unsupported claims, missing steps, and the strongest opposing argument.

In plain words
What is it for?
Use it to test whether a strategy document can withstand skeptical review before sharing it. It provides critique while leaving the rewrite to the author.
Why use it?
Authors often fill in missing context from memory, while a first-time reader may see confusing or weak parts immediately.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to test whether a strategy document can withstand skeptical review before sharing it. It provides critique while leaving the rewrite to the author.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/waddling-penguin/mogkit/narrative-review
Install

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.

Any agent
npx skills add Waddling-Penguin/mogkit --skill narrative-review
Clone the repo
git clone --depth 1 https://github.com/Waddling-Penguin/mogkit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for narrative-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/waddling-penguin/mogkit/narrative-review/github.svg)](https://agentmods.dev/skills/waddling-penguin/mogkit/narrative-review)
Your own site
<a href="https://agentmods.dev/skills/waddling-penguin/mogkit/narrative-review"><img src="https://agentmods.dev/badge/skills/waddling-penguin/mogkit/narrative-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.

agentmods 80×15 button for narrative-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/waddling-penguin/mogkit/narrative-review"><img src="https://agentmods.dev/badge/skills/waddling-penguin/mogkit/narrative-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,143 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00004 $0.01143
Opus 5 $0.00002 $0.00571
Sonnet 5 $0.00001 $0.00229
Haiku 4.5 $0.00000 $0.00114

Measured 10d ago against content hash 0443db5389e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

narrative-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 10d 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.

skills/standalone/narrative-review/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

A strategy memo's author has the argument fully in their head. Reading their own draft, they fill the gaps from memory. An exec reading it for the first time does not have that mental scaffolding — and the good execs read with a question in mind: "where is this weakest?" This skill reads the doc that way.

It surfaces where the narrative leans on hand-waves, where claims are stated as facts, where the logical chain skips a step, and what the strongest counterargument is. It explicitly steel-mans the counter-position the doc is implicitly arguing against.

It does NOT rewrite the narrative. It does not suggest replacement paragraphs. It does not produce a "stronger version" of the argument. The author wrote the narrative; the author owns the rewrite. The point of this skill is to make the author a sharper thinker, not to outsource the prose.

Procedure

  1. Read the doc end to end. Note the central claim — the one sentence the whole narrative is trying to make true.
  2. Map the argument structure as a chain: premise → premise → conclusion. Each link should be a discrete claim. If a "premise" is actually three claims smashed together, separate them.
  3. For each link, classify it: a. Supported — the doc gives evidence (data, citation, mechanism) that would convince a skeptic. b. Asserted — the doc states it as fact without supporting it. Flag this; this is a claim-presented-as-fact. c. Hand-waved — the doc gestures at the link but does not connect it (phrases like "obviously", "clearly", "as is well known", or a single sentence covering what should be a paragraph of reasoning). d. Missing — the conclusion depends on this link but the doc never states it.
  4. Identify the strongest counterargument — the version a smart, informed skeptic would mount. Steel-man it: write the version that would actually give the author trouble, not a straw man. If the doc engages this counter at all, note where; if not, that's a structural gap.
  5. Identify what a skeptic attacks first — the single weakest link in the chain. This is where the author's prep time has the highest return.
  6. Note any claims-presented-as-facts the doc treats as settled when they are actually contested in the field or in the company's own context.
  7. Emit the output contract. Do not propose replacement language for any section of the doc.

Read the full file on GitHub · 103 lines

Changes

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.

  1. 10d ago First seen · 103 lines · 4 tokens per session scan A 0443db5389e3

Subscribe to this mod's changes

narrative-review is a skill published in the GitHub repository Waddling-Penguin/mogkit (5 stars, last pushed 3mo ago), licensed MIT. It adds 4 tokens to every session and 1,143 once invoked, about $0.0000 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.

Related

Other skills, from other repositories

find-skills

Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using the SkillKit CLI. Supports browsing official partner collections (Anthropic, Vercel, Supabase, Stripe, and more) and community repositories, searching by domain or technology, and installing specific skills from…

rohitg00/skillkit · 162 tokens

find-skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

rexleimo/aios · 67 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

interview

Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.

Hmbown/CodeWhale · 40 tokens

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens