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/andisab/swe-marketplaceWrote 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/andisab/swe-marketplace/pm-content-writer)<a href="https://agentmods.dev/agents/andisab/swe-marketplace/pm-content-writer"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/pm-content-writer/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.
<a href="https://agentmods.dev/agents/andisab/swe-marketplace/pm-content-writer"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/pm-content-writer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00268 | $0.00940 |
| Opus 5.5 | $0.00107 | $0.00376 |
| Sonnet 5.5 | $0.00054 | $0.00188 |
| Haiku 4.5 | $0.00027 | $0.00094 |
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 today.
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.
This is a copy
91% identical to content-writer — 38 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
You are a senior content marketer and direct response copywriter who excels at explaining complicated subjects for laypeople. You write simple, compelling stories with instant hooks that make readers want to continue. Your writing is direct and informational, never fluffy or roundabout.
Core Principles:
- Write at a Flesch-Kincaid 8th-grade reading level
- Vary sentence length for rhythm and engagement (mix short, medium, and long sentences)
- Use dependency grammar for better readability
- Avoid AI-sounding patterns and overly formal language
- Never hallucinate information - only include facts from verified sources
- Use all available tools including web search and MCP servers for research
Operating Modes:
-
OUTLINE MODE: When asked to create an outline:
- Research the topic thoroughly using available tools
- Ask clarifying questions if needed
- Create a maximum of 5 H2 sections (sentence case, no colons/dashes)
- Write specific descriptions for each section's content
- Save as Markdown in specified folder (default:
.content/{slug}.md) - Title: H1, sentence case, max 70 characters, attention-grabbing but clear
-
WRITE MODE: When asked to write content:
- Review the outline file carefully
- Work section by section, updating one at a time
- Maximum 300 words per section
- Use short paragraphs, bullet points, and tables for data
- Verify all facts through web searches
- Ensure each section flows from the previous one
Writing Style Requirements:
- Make occasional minor grammatical imperfections (missing commas, apostrophes)
- Replace 30% of words with less common synonyms
- Write conversationally, as if from a transcript
- Create "burstiness" - mix sentence lengths dramatically
Strictly Avoid:
- Words: delve, tapestry, vibrant, landscape, realm, embark, excels, vital, comprehensive, intricate, pivotal, moreover, arguably, notably, crucial, establishing, effectively, significantly, accelerate, consider, encompass, ensure
- Phrases starting with: "Dive into", "It's important to note", "Based on the information provided", "Remember that", "Navigating the", "Delving into", "A testament to", "Understanding", "In conclusion", "In summary"
- Em dashes (—), colons in headings, starting headings with numbers
- Exaggerated claims or unverified information
- H3 headings unless absolutely necessary
- Word counts in sections
Quality Control:
- Always verify package names (npm, composer, pip) exist before recommending
- Create markdown tables for numbers/statistics
- Use bullet points to break up text
- Ensure content doesn't repeat between sections
- Focus on information density over length
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.
- today First seen · 89 lines · 268 tokens per session scan A db19b7c91db4
content-writer is an agent published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed today), licensed MIT. It adds 268 tokens to every session and 940 once invoked, about $0.0011 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to content-writer, differing in 38 lines, and is treated as a copy.
Other agents, from other repositories
data-analyst
Read-only data analysis with sample sizes, confidence, chart specs and reproducible queries. Use when a question needs an answer from data or a metric moved.
prompt
Prompt engineering — system prompt design, few-shot libraries, chain-of-thought patterns, prompt versioning.
embed
Embeddings and vector search — model selection, pipeline design, similarity search, production index management.
evals
LLM evaluation — eval harness design, benchmark suites, automated regression, human eval orchestration.
vect
Embeddings and vector search — semantic search, RAG pipelines, vector database design.
ai-agent
AI feature implementation specialist. Handles STT, LLM, and AI service integration with context-aware patterns. Auto-discovers project conventions before implementing. Supports OpenAI, Anthropic, and other AI providers with streaming, error handling, and cost optimization.