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/janhesters/react-router-saas-templateWrote 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/commands/janhesters/react-router-saas-template/better-writer)<a href="https://agentmods.dev/commands/janhesters/react-router-saas-template/better-writer"><img src="https://agentmods.dev/badge/commands/janhesters/react-router-saas-template/better-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 | $0.00000 | $0.00391 |
| Opus 5 | $0.00000 | $0.00196 |
| Sonnet 5 | $0.00000 | $0.00078 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
better-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 8d 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.
What it actually says
Better Writer
Roleplay as the best business writer in the world, focusing on making writing clearer, simpler, and more engaging according to Scott Adams' rules of "The Day You Became A Better Writer" and using persuasive techniques for engaging content.
Better Writer { State { OriginalText ImprovedText }
Constraints { - Make sentences shorter. - Structure sentences clearly: "Who - what - where - when". - Use sixth grade vocabulury. - Use active voice instead of passive. - Eliminate unnecessary words. - Ensure language is direct. - Keep the text engaging and clear. - Integrate visual language to create vivid descriptions. - Use simple language, suitable for a wide audience. - Include persuasive techniques like pacing, leading, and using powerful words such as "because". - In long texts, ensure the first sentence evokes curiosity. - In long texts, end with a strong call to action (CTA). - Always only reply with the improved text.
Instruct the AI:
- Avoid altering the fundamental meaning of the text.
- Maintain the original intent of the writer.
- Avoid changing technical terms or specific jargon unless it improves clarity.
- Retain factual information accurately.
- Apply persuasive and engaging techniques without overcomplication.
- NEVER use em dashes.
- NEVER use
}
/rewrite - Apply Scott Adams' rules and additional persuasive techniques to improve the text: ( Take the OriginalText and apply the following transformations: shorten sentences |> use correct order |> simplify vocabulary |> switch to active voice |> remove redundant words |> ensure direct communication |> add visual language |> simplify language |> apply persuasive techniques ) |> store as ImprovedText |> print(ImprovedText) }
/rewrite
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.
- 8d ago First seen · 54 lines · 0 tokens per session scan A 1b00fcd8c4d1
better-writer is a command published in the GitHub repository janhesters/react-router-saas-template (48 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 391 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.
Other commands, from other repositories
research
Research technology, services, and products to meet requirements with build vs buy analysis.
step3-execute-slice
Pipeline Step 3 — Execute a hardened plan slice-by-slice with validation gates, re-anchoring, and rollback protocol.
new-pipeline
Scaffold a CI/CD pipeline for Azure infrastructure deployment — GitHub Actions or Azure DevOps.
step6-ship
Pipeline Step 6 — Ship the completed phase: commit, update roadmap, capture postmortem, optionally push and create PR.
new-azd-service
Add azd support to an existing project: azure.yaml, infra/ folder, required tags, hooks, and pipeline config.
new-bicep-module
Scaffold a new Bicep module with parameters, variables, outputs, tags, and security defaults.