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 Azzygoatcoder/agent-useful-skills --skill md-format-fixergit clone --depth 1 https://github.com/Azzygoatcoder/agent-useful-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/azzygoatcoder/agent-useful-skills/md-format-fixer)<a href="https://agentmods.dev/skills/azzygoatcoder/agent-useful-skills/md-format-fixer"><img src="https://agentmods.dev/badge/skills/azzygoatcoder/agent-useful-skills/md-format-fixer/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/azzygoatcoder/agent-useful-skills/md-format-fixer"><img src="https://agentmods.dev/badge/skills/azzygoatcoder/agent-useful-skills/md-format-fixer.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 | $0.00097 | $0.01025 |
| Opus 5.5 | $0.00039 | $0.00410 |
| Sonnet 5.5 | $0.00019 | $0.00205 |
| Haiku 4.5 | $0.00010 | $0.00103 |
Grade A, and why
md-format-fixer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 24d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown Format Fixer
After every Write or Edit to a .md file, run through the checks below on the file
you just touched. Fix issues in place unless flagged for manual review.
Check 1: Tables — blank lines
Problem: A markdown table immediately after a text line (without a blank line between) can be misparsed by some renderers (Obsidian, GitHub, strict CommonMark).
Detection: Any line matching ^|.*|$ that is preceded by a non-empty, non-table,
non-blank line.
Fix: Insert a blank line before the table header row.
Check 2: Code blocks — closing fence
Problem: Content that should be outside a code block is trapped inside because the closing ``` is missing or placed after that content.
Detection: Looking for lines of plain text between the last content line and the closing ``` of a fenced code block.
Fix: Move the closing ``` to before the escaped content, so the content renders as normal markdown.
Manual flag: If no closing ``` exists at all, add one at the end — but warn the user to verify the intended scope.
Check 3: Table column counts
Problem: A data row has fewer or more |-separated cells than the header row or
separator row, causing rendering breakage.
Detection: Count the number of | in the header row, separator row, and each
data row. Any mismatch is an error.
Fix:
- Missing cell: Insert an empty cell
- Extra cell: Merge or remove — flag for manual review if ambiguous.
Check 4: Code blocks — empty fences
Problem: ``` on a line by itself with no matching close creates an unterminated
code block that swallows all subsequent content.
Detection: Any ``` that opens a code block but has no matching close before EOF
or before another code block opens.
Fix: Add a closing ``` at the end of the intended block. If the intended scope
is unclear, flag for manual review.
Check 5: Ambiguous table headers
Problem: Column headers that don't convey what the column represents (e.g., just "差距" without specifying "A − B 差距", or single-word labels that are meaningless without context).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 24d ago First seen · 109 lines · 97 tokens per session scan A f0a075dc80a5
md-format-fixer is a skill published in the GitHub repository Azzygoatcoder/agent-useful-skills (9 stars, last pushed 22d ago), licensed MIT. It adds 97 tokens to every session and 1,025 once invoked, about $0.0004 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 2026-09-22.
Other skills, from other repositories
workdsh-expert-manager
A workflow for creating and delivering reusable expert roles or teams from a user's goals and source material. It saves their instructions, documents, resources, and team structure as a draft that can be checked and published.
workdsh-ppt-design
A workflow guide for creating and editing PowerPoint presentations in the WorkDSH editor. It covers slide-by-slide storytelling, visual design, supported content tools, importing existing PPTX files, and exporting presentations.
workdsh-web-design
A workflow guide for designing and building websites, landing pages, and web applications. It covers content structure, visual styles, responsive layouts, bilingual content, interactions, previews, and delivery within the supported WorkDSH tools.
workdsh-excel-design
A workflow guide for designing, analyzing, and reviewing Excel workbooks. It covers field definitions, data sources, formulas, workbook structure, usability checks, and supported spreadsheet operations.
workdsh-word-design
A workflow guide for creating and formatting Word reports, proposals, meeting notes, and similar documents. It covers document structure, headings, tables, layout, review, and delivery as DOCX files within the supported tools.
dsh-plugin-dev
An authoritative development guide for DeepSeek Harness plugins. DeepSeek Harness is a system where models, tools, services, events, and adapters are built as plugins.