concept-summary-narrator

concept-summary-narrator is an agent for Claude Code from cogni-work/insight-wave. It costs 41 tokens per session (2,219 once invoked), scanned A, original, Apache-2.0.

An agent that rewrites the summary of a topic, organization, or person page using its complete set of collected claims. Claims are individual factual statements supported by research sources.

In plain words
What is it for?
Use it to refresh wiki summaries after a research run adds or merges claims.
Why use it?
It keeps summaries accurate and coherent as new evidence is added. It changes only the summary, leaving claims, links, and source information intact.

Agent for Claude Code

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

Part of the cogni-knowledge plugin — 23 skills, 16 agents shipped together

Good fit Use it to refresh wiki summaries after a research run adds or merges claims.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cogni-work/insight-wave/concept-summary-narrator
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-knowledge, the plugin that ships this one along with the rest of its 23 skills, 16 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 concept-summary-narrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/concept-summary-narrator.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/concept-summary-narrator)
Your own site
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/concept-summary-narrator"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/concept-summary-narrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,219 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 $0.00041 $0.02219
Opus 5 $0.00020 $0.01110
Sonnet 5 $0.00008 $0.00444
Haiku 4.5 $0.00004 $0.00222

Measured 7d ago against content hash d041abe0e73f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

concept-summary-narrator 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 7d 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-knowledge/agents/concept-summary-narrator.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Concept Summary Narrator Agent (inverted pipeline, Phase 4.5)

Role

You read a bundle of distilled pages (concept / entity / person) that gained claims in this distill run. For each, you are given its current ## Summary prose and the full set of merged claims now on the page. You rewrite the summary as a crisp 2–4 sentence prose synthesis that integrates the merged evidence, in OUTPUT_LANGUAGE. You write these as a raw-text renarrate-records file; the knowledge-distill orchestrator runs concept-store.py renarrate to swap each page's summary block.

You do not write wiki pages. You do not build JSON or YAML. You touch only the summary — never the claim list, related list, sources, or notes.

Input Parameters

Parameter Required Description
RENARRATE_BUNDLE_PATH Yes Absolute path to the per-slug bundle. One block per page: a ## slug: <slug> header, a ### current-summary section (the existing prose), and a ### claims section (one - bullet per merged claim text). Your only evidence — do not read the wiki pages or fetch anything.
RECORDS_OUTPUT_PATH Yes Absolute path to write your raw-text renarrate-records file.
OUTPUT_LANGUAGE No ISO 639-1 code (default en). The summary prose is authored in this language (matching the claims' language — DE base → German, with correct ä/ö/ü/ß).

Read the full file on GitHub · 159 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. 7d ago First seen · 159 lines · 41 tokens per session scan A d041abe0e73f

Subscribe to this mod's changes

concept-summary-narrator is an agent published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 2,219 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories