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 derailed-dash/dazbo-agent-skills --skill convert-to-devtogit clone --depth 1 https://github.com/derailed-dash/dazbo-agent-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/derailed-dash/dazbo-agent-skills/convert-to-devto)<a href="https://agentmods.dev/skills/derailed-dash/dazbo-agent-skills/convert-to-devto"><img src="https://agentmods.dev/badge/skills/derailed-dash/dazbo-agent-skills/convert-to-devto/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/derailed-dash/dazbo-agent-skills/convert-to-devto"><img src="https://agentmods.dev/badge/skills/derailed-dash/dazbo-agent-skills/convert-to-devto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.01428 |
| Opus 5 | $0.00026 | $0.00714 |
| Sonnet 5 | $0.00011 | $0.00286 |
| Haiku 4.5 | $0.00005 | $0.00143 |
Grade A, and why
convert-to-devto 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 11d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert technical editor. Your goal is to "fix" the supplied markdown content so that it is suitable for a Dev.to post.
Apply the following rules to the supplied content:
-
Insert a blank line after all markdown headings: In the raw md, any heading should have a blank line after it, before the content. If the first heading of the document is not at H1, fix it. Do not start a list immediately after a heading, without a blank line.
-
Remove User Highlights: Remove any lines that match the pattern " highlighted". These artifacts often appear in exports from other platforms.
-
Fix Code Blocks: Look for triple-backtick code blocks that are missing a language identifier. Examine the code inside and add the correct language prefix (e.g.,
python,bash,javascript, etc.). -
Preserve spacing inside any fenced blocks.
-
Handle Nested Code Blocks: The content may contain a fenced markdown block that in turn contains nested code blocks, e.g. markdown that contains a bash script sample. In this scenario, the outer markdown block should be converted from triple-backticks to triple-tildes. E.g. this:
Code sample: ```bash some codeShould be converted to this: ~~~markdown Code sample: ```bash some code -
Remove Unnecessary Escapes: Look for escape characters that are not required. E.g.
code\_styleguidesshould becode_styleguides. E.g. **Summarize Files** -> Summarize Files. E.g. file_reader_agent should be file_reader_agent. -
Format Inline Variables: Look for strings in the text (NOT inside existing code blocks or links) that appear to be variables (snake_case) or file paths. Wrap them in single backticks so they render as inline code. E.g. file_reader_agent ->
file_reader_agent -
Ensure bold variables or paths are properly single-quoted and surrounded by bold markers. E.g. Generate llms.txt -> Generate
llms.txtE.g. file_reader_agent ->file_reader_agentAlways ensure these variables and paths are properly closed. -
Fix Image Captions: Convert split image/caption styling to standard Markdown image syntax. E.g.
- Before fixing:
My Caption - After fixing:

- Before fixing:
-
Frontmatter Check: Ensure valid YAML frontmatter exists at the top. - Ensure the frontmatter follows strict YAML syntax. - Use double quotes for string values that might contain special characters (like dates or TITLES). - If missing, create it. - Ensure the following keys exist (add with placeholders/defaults if missing):
title: Extract from the first H1 or use "TODO: Title"published: falsedate:current datetime in the format yyyy-mm-dd HH:mm:ss UTCtags: todo1, todo2canonical_url: "TODO"cover_image: "TODO"
-
Liquid Tags: Convert standalone Twitter and YouTube links to Dev.to Liquid tags.
- If a Twitter or YouTube link is part of a sentence, extract it to its own line (preceded and followed by a blank line) and then convert it to a Liquid tag.
- Twitter/X:
https://twitter.com/user/status/123orx.com/...->{% twitter 123 %} - Exceptions:
- DO NOT convert GitHub links to liquid tags; keep them as standard links.
- DO NOT convert YouTube links that appear inside URL bullet lists or reference sections (such as "Useful Links and References", "Project Demo & Portfolio", etc.). Keep them as standard Markdown links (e.g.
- [FinSavant YouTube Demo](https://www.youtube.com/watch?v=zs_IRUxIx4E)) to avoid interrupting link lists with large embeds.
- YouTube:
https://youtube.com/watch?v=123oryoutu.be/123->{% youtube 123 %}
-
Check heading structure: The post title should only be in the front matter
title. It should not be repeated in the markdown content. Subsequently, all top-level headings in the md content should be H2 (##). Ensure that sub-headings are at the appropriate level. For example, any H1 headings in the provided markdown content should be converted to H2, and all subsequent heading levels (H2, H3, etc) should be demoted accordingly to maintain a logical hierarchy. -
Liquid/Jekyll Escaping & Code Block Delimiters:
- Do NOT use
{% raw %}or{% endraw %}tags around or inside code blocks. DEV.to does not support therawLiquid tag in user posts, and including them will trigger aLiquid syntax error: Unknown tag 'endraw'page rendering crash. - Inside standard fenced code blocks (using either triple-backticks
```or triple-tildes~~~), DEV.to natively disables Liquid compilation. Write all YAML or code snippets containing double curly braces (like${{ secrets.GEMINI_API_KEY }}) exactly as-is, without any escaping. - If a standard backtick block (
```tomlor```ini) renders with the language name displayed literally at the top, convert it to a tilde block (e.g.~~~tomlor~~~~toml) to bypass the highlighting parser glitch.
- Do NOT use
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.
- 11d ago First seen · 99 lines · 53 tokens per session scan A 1f5f890d9968
convert-to-devto is a skill published in the GitHub repository derailed-dash/dazbo-agent-skills (24 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 1,428 once invoked, about $0.0003 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 skills, from other repositories
learning-quality
Structured format for capturing high-quality learnings during ClosedLoop runs.
plan-validate
Deterministic plan.json validation via Python script, replacing most plan-validator agent calls. Performs JSON parsing, schema validation, task checkbox regex, required section checks, sync validation, and data extraction. Only semantic consistency checks (storage/query alignment) require the LLM agent. Triggers on…
openai-docs
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use…
Presentations
Read, create or edit PowerPoint or Google Slides decks. Use for presentation, slide deck, PowerPoint, PPT, PPTX, or Google Slides requests.
intuitive-squash
Squash local GSD or agent-generated commit history into a clean, reviewable story while preserving important fixes. Use when the user asks to squash commits, clean git history, compress phase commits, prepare a branch before PR, compare aggressive vs moderate squash options, or preserve hotfix/security commits during…
intuitive-refactor
Refactor and cleanup router for known code/module/API seams, stale surfaces, compatibility shims, architecture cleanup targets, changed-code quality review, oversized modules, repeated cleanup campaigns, and recurring whole-repo architecture maintenance goals. Use this when the user names a concrete seam, wants…