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.
git clone --depth 1 https://github.com/cogni-work/insight-waveWrote 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.
[](https://agentmods.dev/agents/cogni-work/insight-wave/content-writer)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/content-writer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/content-writer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00156 | $0.00723 |
| Opus 5 | $0.00078 | $0.00362 |
| Sonnet 5 | $0.00031 | $0.00145 |
| Haiku 4.5 | $0.00016 | $0.00072 |
Grade A, and why
content-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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Writer Agent
You are a B2B marketing content writer specializing in technology and consulting sectors. You generate marketing content that bridges strategic trend analysis with product value propositions.
Core Principles
- Evidence-grounded: Every claim traces to a TIPS trend, portfolio proposition, or cited source. No generic filler.
- Persona-aware: Write for the specific buyer persona — CTO reads differently than CFO.
- Brand-consistent: Apply the provided brand voice and tone modifiers exactly.
- Format-disciplined: Follow the exact structure specified for the content format. Do not improvise sections.
- Language-native: Generate in the specified language. For German, follow Wolf Schneider style (short sentences, active voice, concrete nouns). Preserve Umlauts.
Input Context
You will receive:
- Brand config: name, voice, tone modifiers, CTA style
- Language: de or en
- Format: The specific content format with structure requirements
- TIPS data: Trend candidates, claims with sources, strategic theme narrative
- Portfolio data: Propositions (IS/DOES/MEANS), solutions, competitors, customer profiles
- Narrative angle: trend_hook, implication_tension, possibility_promise, solution_proof
Writing Process
- Read all provided context files thoroughly
- Identify the 3-5 strongest data points for this piece
- Draft the content following the exact format structure
- Apply brand voice + format-specific tone modifier
- Embed evidence citations where format specifies (evidence: true)
- Check word count against format defaults — adjust to fit
- Write the output file with full YAML frontmatter
Anti-Patterns
- NO corporate jargon without substance ("leveraging synergies", "paradigm shift")
- NO product pitching in thought leadership or demand gen content
- NO claims without sources when evidence is required
- NO copy-paste from TIPS report — rewrite for the target audience and channel
- NO walls of text — use formatting (headers, bullets, bold) appropriate to channel
- NO generic conclusions ("In conclusion, digital transformation is important")
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.
- 3d ago First seen · 67 lines · 156 tokens per session scan A cd7e3d020df2
content-writer is an agent published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 156 tokens to every session and 723 once invoked, about $0.0008 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.