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 skills/terrylica/cc-skills/markdown-table-validatornpx skills add terrylica/cc-skills --skill markdown-table-validatorgit clone --depth 1 https://github.com/terrylica/cc-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/terrylica/cc-skills/markdown-table-validator)<a href="https://agentmods.dev/skills/terrylica/cc-skills/markdown-table-validator"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/markdown-table-validator.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 | $0.00117 | $0.01210 |
| Opus 5 | $0.00059 | $0.00605 |
| Sonnet 5 | $0.00023 | $0.00242 |
| Haiku 4.5 | $0.00012 | $0.00121 |
Grade A, and why
markdown-table-validator 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 today.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown Table Validator
Scan Markdown files for the structural problems that silently demote a GFM table
to a plain paragraph on GitHub / VS Code preview, and optionally auto-escape the
single most common cause (an unescaped | inside a cell).
Self-Evolving Skill: This skill improves through use. If the detector misses a real broken-table case, the
--fixheuristic guesses wrong, or a path/flag has drifted — fix this file (and the detector SSoT) immediately, don't defer. Only update for real, reproducible issues.
Why tables break (the one rule that matters)
GFM ignores whitespace between pipes, so alignment is never the cause. What
breaks rendering is structure — overwhelmingly an unescaped | inside a
cell. GFM's table tokenizer treats a | as a column delimiter even inside a
`code span`, so a regex/code cell like `a | b | c` inflates that
row's cell count and the whole table collapses. The fix — escaping it as \| —
changes meaning, so no formatter does it for you (Prettier actively corrupts
such tables: prettier#10164 / #11410). This skill detects it and can apply the
escape under review.
Quick start
SCAN="$(cc-plugin-root doc-tools)/skills/markdown-table-validator/scripts/scan_markdown_tables.ts"
# Report problems in one file (exit 1 if any render-breaking error)
bun "$SCAN" path/to/FILE.md
# Audit a whole tree
bun "$SCAN" "docs/**/*.md" "plugins/**/*.md"
# Opt-in auto-fix: escape over-count pipes, then re-align with prettier
bun "$SCAN" --fix path/to/FILE.md
prettier --write path/to/FILE.md
What it detects
| Code | Severity | Meaning |
|---|---|---|
column-overflow |
error | A row has more cells than the header → unescaped | in a cell. |
header-mismatch |
error | Header and separator row have different column counts → won't render. |
indented-table |
error | Table indented ≥4 spaces → parsed as a code block. |
alignment-colon-in-row |
error | An alignment token like :--: sits in a data row (misplaced separator). |
short-row |
info | Row has too few cells; GFM pads and markdownlint --fix repairs. |
missing-blank-line |
info | No blank line before/after the table; the formatter auto-fixes. |
What ships with it
2 files 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.
- today First seen · 98 lines · 117 tokens per session scan A e136f7ee2945
markdown-table-validator is a skill published in the GitHub repository terrylica/cc-skills (62 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 1,210 once invoked, about $0.0006 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 2026-09-05.
Other skills, from other repositories
omh-rust
This is a Hermes-native rust workflow skill.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
impact-report-writer
Nonprofit/NGO impact report generation with data visualization suggestions, outcome metrics, narrative structure, and program data presentation. Use when writing impact reports, annual reports, or program evaluation summaries.
bib-coverage
Compare a project .bib against a Paperpile project/topic folder to find uncited papers or unfiled entries. Use when the user asks to compare a project .bib against a Paperpile project/topic folder to find uncited papers or unfiled entries.
mobile-animation-reanimated
React Native Reanimated 4 - shared values, animated styles, spring/timing/decay, layout animations, gesture integration, scroll-driven animations, interpolation, worklets, CSS animations.