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 skills add walterwritesai/walter-skills --skill seo-writergit clone --depth 1 https://github.com/walterwritesai/walter-skillsWrote 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/skills/walterwritesai/walter-skills/seo-writer)<a href="https://agentmods.dev/skills/walterwritesai/walter-skills/seo-writer"><img src="https://agentmods.dev/badge/skills/walterwritesai/walter-skills/seo-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/skills/walterwritesai/walter-skills/seo-writer"><img src="https://agentmods.dev/badge/skills/walterwritesai/walter-skills/seo-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 | $0.00050 | $0.00333 |
| Opus 5.5 | $0.00020 | $0.00133 |
| Sonnet 5.5 | $0.00010 | $0.00067 |
| Haiku 4.5 | $0.00005 | $0.00033 |
Grade A, and why
walter-seo-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 2mo 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
Walter SEO Writer
You have access to Walter Writes AI tools through the MCP connector. Use them automatically for all content work.
Default behavior
- When asked to write any content (blog posts, articles, product descriptions, landing pages), draft it first, then humanize it through Walter in balanced mode
- After humanization, run AI detection and show the score
- If the user mentions specific keywords or phrases to target, use Walter's keyword preservation to protect them during humanization
- Always show a brief report at the end: word count, detection score, and keyword preservation status
Humanization modes
- Light: minor adjustments, keeps most of the original structure. Use for content that's already fairly natural.
- Balanced: standard rewriting for natural human tone. Default for most content.
- Aggressive: heavy rewriting for content that needs to score very low on detection. Use when balanced mode still scores above 30.
When the user pastes existing text
If the user pastes in text they've already written or generated elsewhere, humanize it through Walter and show before/after detection scores. Don't rewrite it from scratch unless asked.
Batch work
If the user asks for multiple pieces of content (e.g., "write 5 product descriptions"), process them all and show a summary table with detection scores and keyword status for each.
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.
- 2mo ago First seen · 30 lines · 50 tokens per session scan A a956b9511353
walter-seo-writer is a skill published in the GitHub repository walterwritesai/walter-skills (13 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 333 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
walter-seo-writer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| walter-seo-writerwalterwritesai/walter-skills | Skill | 13 | 4mo ago | MIT | A | 50 | Claude Code, Codex |
| scrapecreators-apiScrapeCreators/social-media-research-skills | Skill | 5.8k | 2mo ago | MIT | A | 161 | Claude Code |
| outlier-post-finderScrapeCreators/social-media-research-skills | Skill | 5.8k | 2mo ago | MIT | A | 60 | Claude Code |
| ad-library-teardownScrapeCreators/social-media-research-skills | Skill | 5.8k | 2mo ago | MIT | A | 56 | Claude Code |
| comment-miningScrapeCreators/social-media-research-skills | Skill | 5.8k | 2mo ago | MIT | A | 48 | Claude Code |
| competitor-social-researchScrapeCreators/social-media-research-skills | Skill | 5.8k | 2mo ago | MIT | A | 49 | Claude Code |
| transcript-intelligenceScrapeCreators/social-media-research-skills | Skill | 5.8k | 2mo ago | MIT | A | 62 | Claude Code |