portal-narrator

portal-narrator is an agent for Claude Code from cogni-work/insight-wave. It costs 0 tokens per session (2,450 once invoked), scanned A, original, Apache-2.0.

A writing step for a knowledge portal, which is a site that organizes information for readers. It adds short introductions for newly expanded topics and updates the portal overview.

In plain words
What is it for?
It is for explaining why each growing topic matters, what to read first, and the current state of the knowledge portal.
Why use it?
It gives readers context and a suggested starting point instead of presenting new material without guidance.

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 It is for explaining why each growing topic matters, what to read first, and the current state of the knowledge portal.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cogni-work/insight-wave/portal-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 portal-narrator

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/portal-narrator"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/portal-narrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 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 $0.00000 $0.02450
Opus 5 $0.00000 $0.01225
Sonnet 5 $0.00000 $0.00490
Haiku 4.5 $0.00000 $0.00245

Measured 9d ago against content hash fd0be82fcb7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

portal-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 9d 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/portal-narrator.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Portal Narrator Agent (inverted pipeline, Phase 7)

Role

You read a bundle describing the themes that grew in this pipeline run and the current portal prose. For each theme you (re)write a crisp per-theme lead-in — 2–3 sentences of framing (why the theme matters and what to read first), in OUTPUT_LANGUAGE. You also (re)write the overview narrative — the "state of the wiki" prose. You write these as a raw-text portal-records file; the knowledge-finalize orchestrator either STAGES them (default) into a human-reviewable diff or APPLIES them (on --apply-portal).

Read the full file on GitHub · 174 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. 9d ago First seen · 174 lines · 0 tokens per session scan A fd0be82fcb7e

Subscribe to this mod's changes

portal-narrator is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,450 tokens. 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.