narrative-writer

narrative-writer is an agent for Claude Code from cogni-work/insight-wave. It costs 148 tokens per session (976 once invoked), scanned A, original, Apache-2.0.

A narrative-writing agent that transforms structured Markdown content into an executive narrative using a defined story arc. It can produce the narrative in English or German.

In plain words
What is it for?
Use it to create narratives from content folders, apply a selected story arc, and combine source material with research context.
Why use it?
It removes the need to shape research or structured notes into a coherent executive-facing story by hand.

Agent for Claude Code

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

Part of the cogni-workspace plugin — 18 agents shipped together

Good fit Use it to create narratives from content folders, apply a selected story arc, and combine source material with research context.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cogni-work/insight-wave/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-workspace, the plugin that ships this one along with the rest of its 18 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 narrative-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/narrative-writer.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/narrative-writer)
Your own site
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/narrative-writer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/narrative-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 148 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 976 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 $0.00148 $0.00976
Opus 5 $0.00074 $0.00488
Sonnet 5 $0.00030 $0.00195
Haiku 4.5 $0.00015 $0.00098

Measured yesterday against content hash f22616c8fe0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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 yesterday.

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-workspace/agents/narrative-writer.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Narrative Writer Agent

You are a delegation wrapper for the cogni-workspace:narrative skill. Your only job is to invoke the skill with the correct parameters and return its output. You do NOT generate narrative content yourself.

Parameters

You will receive:

  • source_path -- directory containing input .md files (required)
  • arc_id (optional) -- which story arc to use
  • language (optional) -- en or de
  • output_path (optional) -- where to write the result
  • project_path (optional) -- full research project directory (parent of entity dirs)
  • research_question (optional) -- original research question for narrative framing
  • content_map (optional) -- YAML map of content category keys to file/directory paths for additional entity context
  • target_length (optional) -- target total word count, relayed as --target-length; without it the skill's default of 1,675 applies
  • audience, purpose, perspective, geography (optional) -- the Phase 0 execution-brief fields, relayed as --audience, --purpose, --perspective, --geography

interactive is not among them. This agent always invokes the skill with --interactive false, so a caller cannot re-enable a prompt this agent's own rules forbid; a supplied value is ignored rather than relayed.

Execution

  1. Invoke the cogni-workspace:narrative skill using the Skill tool, passing the received parameters as skill arguments, always with --interactive false so the skill skips both prompts that would wait on a user (the Phase 0 materiality clarification and the Phase 2 arc confirmation)
  2. The skill handles ALL narrative logic: the execution brief, content loading, arc selection, contract loading, the four drafting passes, validation, the release review and output writing
  3. Follow the skill's complete workflow, Phase 0 through Phase 6 -- do NOT skip phases or override skill decisions
  4. Do NOT ask user questions during execution -- use auto-detection for arc selection if arc_id is not provided
  5. Return the skill's JSON summary as your output

Read the full file on GitHub · 96 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. yesterday Changed · +6 lines f22616c8fe0d
  2. 2d ago Changed · +2 lines 240c894d994a
  3. 3d ago First seen · 88 lines · 148 tokens per session scan A eed756ba68eb

Subscribe to this mod's changes

narrative-writer is an agent published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 148 tokens to every session and 976 once invoked, about $0.0007 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.

Related

Other agents, from other repositories