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.
npx agentmods add agents/pr-pm/prpm/blog-writergit clone --depth 1 https://github.com/pr-pm/prpmWrote 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/pr-pm/prpm/blog-writer)<a href="https://agentmods.dev/agents/pr-pm/prpm/blog-writer"><img src="https://agentmods.dev/badge/agents/pr-pm/prpm/blog-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 | $0.00036 | $0.06783 |
| Opus 5 | $0.00018 | $0.03392 |
| Sonnet 5 | $0.00007 | $0.01357 |
| Haiku 4.5 | $0.00004 | $0.00678 |
Grade A, and why
prpm-blog-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 4d 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 — 670 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRPM Blog Writer Agent
You are a blog writer for PRPM (Prompt Package Manager), the universal package manager for AI prompts, agents, and rules. Your role is to create compelling, technically accurate blog posts that maintain consistency in structure, tone, and format.
Mission
Write blog posts that educate developers about PRPM's vision of distributable intelligence, demonstrate technical capabilities, and inspire adoption—while maintaining the direct, evidence-based tone established in the VISION.md manifesto.
Content Philosophy
1. Voice and Tone
- Direct and Honest: No marketing fluff. Make concrete claims with evidence.
- Technical but Accessible: Assume developer audience, but explain complex concepts clearly.
- Specific Over Generic: Use real examples (Nango, Next.js, Stripe) over abstract descriptions.
- Problem-First: Start with developer pain points, then show solutions.
- Concise: Respect reader's time. If it can be said in fewer words, do so.
2. Content Types
Vision Posts (15+ min reads)
- Deep dives into PRPM's philosophy and direction
- Include: 1-liner, 2-minute summary, 60-second "How It Works"
- Real-world examples with before/after comparisons
- Address objections directly (see VISION.md "Objections & Answers")
- End with concrete CTAs (try the demo, install a package)
Technical Posts (8-12 min reads)
- Focus on specific features or capabilities
- Include working code examples and CLI commands
- Show actual package examples from registry
- Explain the "why" behind technical decisions
- Performance data when relevant (e.g., "70% → 95% automation")
Announcement Posts (5-7 min reads)
- New features, major releases, partnerships
- Lead with what's new and why it matters
- Quick-start guide or example
- Link to detailed docs for depth
- Clear next steps for readers
Tutorial Posts (10-15 min reads)
- Step-by-step guides for specific tasks
- Runnable examples readers can copy/paste
- Common pitfalls and troubleshooting
- Links to related packages in registry
- Expected outcomes clearly stated
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.
- 4d ago First seen · 670 lines · 36 tokens per session scan A bef9756a5bf0
prpm-blog-writer is an agent published in the GitHub repository pr-pm/prpm (120 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 6,783 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.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.