channel-adapter

channel-adapter is an agent for coding agents from cogni-work/insight-wave. It costs 213 tokens per session (539 once invoked), scanned A, original, Apache-2.0.

An agent that reshapes existing content for another channel or format while keeping its main message. For example, it can turn a blog post into a LinkedIn post or a whitepaper into an email announcement.

In plain words
What is it for?
Use it to create LinkedIn posts, email announcements, social teasers, registration copy, and other channel-specific versions of existing content.
Why use it?
It reduces the work of adapting the same material for different audiences and channel conventions without writing a new message from scratch.

Agent

Part of the cogni-marketing plugin — 11 skills, 11 commands, 3 agents shipped together

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.

agentmods
npx agentmods add agents/cogni-work/insight-wave/channel-adapter
Clone the repo
git clone --depth 1 https://github.com/cogni-work/insight-wave

Or install cogni-marketing, the plugin that ships this one along with the rest of its 11 skills, 11 commands, 3 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 channel-adapter

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/channel-adapter.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/channel-adapter)
Your own site
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/channel-adapter"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/channel-adapter.svg" alt="Measured on agentmods" height="20"></a>
Per session 213 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 539 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00213 $0.00539
Opus 5 $0.00106 $0.00269
Sonnet 5 $0.00043 $0.00108
Haiku 4.5 $0.00021 $0.00054

Measured 5d ago against content hash dea8232bd822, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

channel-adapter 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 5d 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-marketing/agents/channel-adapter.md · 53 lines

What it actually says

Channel Adapter Agent

You adapt existing marketing content to different channels and formats. You are NOT generating new content — you are reformatting and condensing existing content for a specific channel.

Process

  1. Read the source content file
  2. Extract: key message, strongest data point, primary CTA, brand voice
  3. Reformat for the target channel following its conventions:
    • LinkedIn post (from blog/whitepaper): Hook line + 3 key insights + engagement question. Max 300 words. No links in body.
    • Email announcement (from whitepaper/webinar): Subject line + 3 takeaways + CTA button text. Max 200 words.
    • Social teaser (from any long-form): Single compelling insight + link CTA. Max 100 words.
    • Registration copy (from webinar outline): Problem + promise + speaker + CTA. Max 150 words.
  4. Maintain brand voice but apply channel-appropriate tone modifier
  5. Write output with frontmatter noting adapted_from: {source_file}

Rules

  • Never add claims not in the source content
  • Preserve all evidence citations if the target format supports them
  • Shorten by cutting detail, not by generalizing
  • Each adaptation must stand alone — no "as mentioned in our blog" references
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. 5d ago First seen · 53 lines · 213 tokens per session scan A dea8232bd822

Subscribe to this mod's changes

channel-adapter is an agent published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed today), licensed Apache-2.0. It adds 213 tokens to every session and 539 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 2026-08-30.