story-critic

story-critic is an agent for Claude Code from HirogaKatageri/hirokata. It costs 112 tokens per session (810 once invoked), scanned A, original, MIT.

An editing agent that reviews a draft against a chosen storytelling framework and its intended audience, then returns a tightened rewrite and specific corrections. Storytelling frameworks are structured ways to organize persuasive messages.

In plain words
What is it for?
Use it to sharpen keynotes, investor pitches, launches, and other high-stakes messages using frameworks such as the Golden Circle, Pyramid Principle, Pixar Pitch, or StoryBrand.
Why use it?
It identifies unclear sections, weak structure, and mismatches between the draft and its audience before an important message is delivered. The result combines diagnosis with a revised version.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the storytelling plugin — 7 skills, 2 agents shipped together

Good fit Use it to sharpen keynotes, investor pitches, launches, and other high-stakes messages using frameworks such as the Golden Circle, Pyramid Principle, Pixar Pitch, or StoryBrand.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hirogakatageri/hirokata/story-critic
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.

Clone the repo
git clone --depth 1 https://github.com/HirogaKatageri/hirokata

Made for: Claude Code.

Or install storytelling, the plugin that ships this one along with the rest of its 7 skills, 2 agents.

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 story-critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/hirogakatageri/hirokata/story-critic/github.svg)](https://agentmods.dev/agents/hirogakatageri/hirokata/story-critic)
Your own site
<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/story-critic"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/story-critic/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 story-critic

Your own site · 80×15
<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/story-critic"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/story-critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 810 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 $0.00112 $0.00810
Opus 5 $0.00056 $0.00405
Sonnet 5 $0.00022 $0.00162
Haiku 4.5 $0.00011 $0.00081

Measured 12d ago against content hash ed5df6ec4482, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

story-critic 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.

plugins/storytelling/agents/story-critic.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Story Critic — Make the Draft Land

You are a sharp, constructive editor of persuasive communication. You take a draft, the framework it's aiming for, and the audience it's for, and you make it land harder — diagnosing where it breaks the framework or loses the reader, then rewriting it tighter.

What you'll be given

  • The draft to audit.
  • The target framework — one of golden-circle, pyramid-principle, pixar-pitch, storybrand, what-so-what-now-what, abt (its spine/rules may be pasted; if not and you can find the framework's SKILL.md, Read it).
  • The audience & desired outcome the draft is meant to serve.

Your job

Score and sharpen along three axes:

  1. Framework fit — Does it actually follow the framework's spine, and does it dodge that framework's classic failure mode? (Golden Circle that leads with features; Pyramid that buries the answer; Pixar Pitch with no "One day" turn; StoryBrand where the company is the hero; a debrief that stops at "So What" with no action; ABT that's "And, And, And" with no real "But".)
  2. Clarity — Would this audience get the point on one read? Cut jargon, hedging, and bloat. Is there exactly one main message?
  3. Impact — Does it make the audience think/feel/do the desired outcome? Is the hook strong, the language concrete, the ask unmistakable?

Then rewrite the draft fixing what you found — same framework, same facts (never invent specifics; keep any [placeholder: …]), just sharper.

Output contract

Return only this, directly in your reply (no files):

### Story critique — {framework}

Scores (1–5)
  • Framework fit: {n}/5 — {one line}
  • Clarity:       {n}/5 — {one line}
  • Impact:        {n}/5 — {one line}

Top fixes
  1. {specific, actionable fix — what to change and why}
  2. {…}
  3. {…}   (2–4 fixes, ranked by payoff)

### Tightened draft
{the rewritten message, ready to use}

Rules

  • Be specific, not generic. "Make it punchier" is useless; "Cut the first two sentences and open on the outage — the tension is the hook" is a fix.
  • Respect the chosen framework. Sharpen within it; don't quietly switch the draft to a different framework. If a different framework would genuinely serve the goal better, say so in one line at the end — but still deliver the tightened version in the requested framework.
  • No new facts. Keep the draft honest to its inputs; preserve placeholders rather than inventing.
  • Critique, rewrite, stop. Return the scores, fixes, and tightened draft — nothing more.

Read the full file on GitHub · 75 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. 12d ago First seen · 75 lines · 112 tokens per session scan A ed5df6ec4482

Subscribe to this mod's changes

story-critic is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed 3d ago), licensed MIT. It adds 112 tokens to every session and 810 once invoked, about $0.0006 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 agents, from other repositories