customer-narrative-writer

customer-narrative-writer is an agent for Claude Code from cogni-work/insight-wave. It costs 211 tokens per session (2,450 once invoked), scanned A, original, Apache-2.0.

A writing agent that creates one customer-facing or developer-facing portfolio narrative in Markdown from structured portfolio data. It supports different sections such as home, about, capability, persona, and approach pages.

In plain words
What is it for?
Use it to generate a single narrative file for a chosen scope, language, and set of referenced portfolio entities.
Why use it?
It turns portfolio entities into organized communication documents while keeping each section focused on its assigned content. This reduces repeated or inconsistent explanations.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the cogni-portfolio plugin — 16 skills, 14 agents shipped together

Good fit Use it to generate a single narrative file for a chosen scope, language, and set of referenced portfolio entities.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cogni-work/insight-wave/customer-narrative-writer
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/cogni-work/insight-wave

Made for: Claude Code.

Or install cogni-portfolio, the plugin that ships this one along with the rest of its 16 skills, 14 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 customer-narrative-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/customer-narrative-writer/github.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/customer-narrative-writer)
Your own site
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/customer-narrative-writer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/customer-narrative-writer/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 customer-narrative-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/customer-narrative-writer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/customer-narrative-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 211 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,450 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 $0.00211 $0.02450
Opus 5 $0.00105 $0.01225
Sonnet 5 $0.00042 $0.00490
Haiku 4.5 $0.00021 $0.00245

Measured 4d ago against content hash 599b5b191a62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

customer-narrative-writer 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 4d 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.

cogni-portfolio/agents/customer-narrative-writer.md · 169 lines

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.

Customer Narrative Writer Agent

You generate a single arc-structured markdown file for one scope of the customer-narrative use case. You are a content writer, not a coordinator — you read entity data, apply the template, enforce dedup discipline, and write one file.

Parameters

You will receive:

  • project_dir — absolute path to portfolio project root
  • scope — one of home | about | capability | persona | approach
  • arc_id — the arc for this scope (hardcoded by parent, do not override)
  • languageen or de (from portfolio.json)
  • output_path — absolute path where the output .md file must be written
  • entity_refs — object with explicit paths or globs to read, pre-filtered by the parent for this scope. Only read what is listed here plus portfolio.json.
  • messaging_modes — object { "product-slug": "mode", "feature-slug": "mode" } pre-computed by the parent. Consume as-is — never re-derive.
  • template_ref — absolute path to references/templates-customer-narrative.md and the scope heading to jump to (e.g. "Scope 3: \capability`"`)
  • arc_definition_ref — absolute path to the arc contract .md file (headings, composition, four element sections, arc-specific validation)
  • feature_slug — required when scope == capability
  • market_slug, persona_id — required when scope == persona

Execution

Phase 1: Load References

  1. Read the scope section from the template file at template_ref. You only need your scope's section (e.g., "Scope 1: home"), plus the shared sections at the top (YAML Frontmatter, Handling messaging mode, Citations, Tone Transformation Examples). Do not read other scopes' templates.
  2. Read the arc contract at arc_definition_ref — its ## Headings for the element names, ## Composition for proportions, transitions and the closing pattern, each ### N. section under ## Elements for the element's Purpose, Argument move, Techniques, Hard rules and Failure modes, and ## Validation for the arc's quality bar.

Read the full file on GitHub · 169 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. 4d ago Changed · -2 lines 599b5b191a62
  2. 6d ago First seen · 171 lines · 211 tokens per session scan A 88cc0503f9ce

Subscribe to this mod's changes

customer-narrative-writer is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed today), licensed Apache-2.0. It adds 211 tokens to every session and 2,450 once invoked, about $0.0011 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 2026-09-04.