narrative-building

narrative-building is a skill for Claude Code, Codex from Avyayalaya/agent-prime. It costs 85 tokens per session (21,306 once invoked), scanned A, original, MIT.

A method for shaping how a product or initiative is explained to its audience. It builds the reasoning behind its position, timing, evidence, objections, and message.

In plain words
What is it for?
Writing product positioning, launch stories, strategy narratives, stakeholder pitches, and explanations of why an initiative should happen now.
Why use it?
It helps when a product has solid work behind it but customers, leaders, or investors do not yet understand why it matters or why the timing is right.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Writing product positioning, launch stories, strategy narratives, stakeholder pitches, and explanations of why an initiative should happen now.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/avyayalaya/agent-prime/narrative-building
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 Avyayalaya/agent-prime --skill narrative-building
Clone the repo
git clone --depth 1 https://github.com/Avyayalaya/agent-prime

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-building

README.md
[![agentmods](https://agentmods.dev/badge/skills/avyayalaya/agent-prime/narrative-building/github.svg)](https://agentmods.dev/skills/avyayalaya/agent-prime/narrative-building)
Your own site
<a href="https://agentmods.dev/skills/avyayalaya/agent-prime/narrative-building"><img src="https://agentmods.dev/badge/skills/avyayalaya/agent-prime/narrative-building/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-building

Your own site · 80×15
<a href="https://agentmods.dev/skills/avyayalaya/agent-prime/narrative-building"><img src="https://agentmods.dev/badge/skills/avyayalaya/agent-prime/narrative-building.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 21,306 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 $0.00085 $0.21306
Opus 5 $0.00043 $0.10653
Sonnet 5 $0.00017 $0.04261
Haiku 4.5 $0.00009 $0.02131

Measured 10d ago against content hash aeba52fac4b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

narrative-building 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

shared/toolkits/skills/narrative-building/SKILL.md · 1,211 lines

How it starts

The opening of the file, as written. The whole thing — 1,211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Produce an elite-tier Strategic Narrative Document that constructs the story making a product, feature, or strategy feel inevitable — not by assertion but by structural argument. The output is not a tagline or a slide deck outline; it is a narrative engineering system: a structural spine, audience-adapted variants, evidence-integrated claims, pre-embedded objection responses, and a testing protocol that validates the narrative before it goes live.

When to Use / When NOT to Use

Use this skill when:

  • Positioning a new product or repositioning an existing one in a competitive market
  • Preparing a board deck, investor pitch, or executive strategy narrative
  • Writing the "why now" story for a product launch or market entry
  • Crafting the internal alignment narrative ("here's why we're doing this and not that")
  • Building a launch narrative for press, analyst briefings, or customer communications
  • Translating competitive analysis findings into a positioning story (downstream of Competitive Analysis)
  • A product has strong fundamentals but the story isn't landing with stakeholders or customers

Do NOT use this skill when:

  • You need competitive analysis (use Competitive & Market Analysis skill first — this skill consumes its output, it does not produce it)
  • You need to define what to build (use Specification Writing skill — narrative follows strategy, not the other way around)
  • You need customer discovery or research synthesis (use Discovery & Research skill — that's primary research, this is narrative construction from existing inputs)
  • You need metric design or success measurement (use Metric Design & Experimentation skill)
  • You need a tagline, slogan, or brand identity system (this skill produces strategic narrative, not copy)

Anti-inputs (what this skill does NOT handle):

  • Customer interview synthesis (-> Discovery & Research skill)
  • Competitive landscape mapping (-> Competitive & Market Analysis skill)
  • Product specification (-> Specification Writing skill)
  • Marketing copy, ad copy, or social media content (-> copywriting, not strategic narrative)
  • Visual design for presentations (this produces the narrative structure; design is a separate discipline)

Read the full file on GitHub · 1,211 lines

Files

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.

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 · 1,211 lines · 85 tokens per session scan A aeba52fac4b6

Subscribe to this mod's changes

narrative-building is a skill published in the GitHub repository Avyayalaya/agent-prime (8 stars, last pushed 3mo ago), licensed MIT. It adds 85 tokens to every session and 21,306 once invoked, about $0.0004 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

narrative-building

Use when building product positioning, crafting strategy narratives, preparing stakeholder pitches, writing launch narratives, or constructing the 'why now' story for a product or initiative. Encodes Narrative Arc Construction, April Dunford-inspired Positioning, Why Now analysis, Audience Adaptation…

Avyayalaya/pm-skills-arsenal · 85 tokens

strategy-generate

Create, modify, and optimize quantitative trading strategies, then backtest and evaluate them.

HKUDS/Vibe-Trading · 21 tokens

bottleneck-hunter

Supply-chain bottleneck arbitrage. Given a super-trend (AI infra, energy transition, defense, semiconductor reshoring, space economy), decompose its physical supply chain down to Layer 2/3 choke points (optics, lasers, InP/SOI substrates, IC substrates, probe cards, specialty fiberglass...) and surface under-the-radar…

HKUDS/Vibe-Trading · 145 tokens

execution-model

Trade execution modeling (backtest only) — slippage formulas (linear / square-root impact), VWAP/TWAP execution logic, market-impact cost estimation, and execution-assumption configuration.

HKUDS/Vibe-Trading · 41 tokens

ml-strategy

Machine-learning predictive strategy based on sklearn walk-forward training, feature engineering, and signal generation. Suitable for any OHLCV data.

HKUDS/Vibe-Trading · 30 tokens

event-driven

Event-driven strategy based on sentiment-scored signals from news, announcements, and macro events. The LLM acts as the NLP engine, and event data follows a CSV schema.

HKUDS/Vibe-Trading · 38 tokens