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 cosmix/loom --skill loom-md-tablesgit clone --depth 1 https://github.com/cosmix/loomWrote 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/cosmix/loom/loom-md-tables)<a href="https://agentmods.dev/skills/cosmix/loom/loom-md-tables"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-md-tables/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/cosmix/loom/loom-md-tables"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-md-tables.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 | $0.00013 | $0.00856 |
| Opus 5 | $0.00006 | $0.00428 |
| Sonnet 5 | $0.00003 | $0.00171 |
| Haiku 4.5 | $0.00001 | $0.00086 |
Grade A, and why
loom-md-tables 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 6d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown Table Formatting
Utility for fixing markdown table alignment and spacing. Normalizes column widths, ensures consistent padding, and preserves alignment markers.
Quick Examples
# Preview fixed output
python fix-md-tables.py document.md
# Fix in-place
python fix-md-tables.py document.md -i
Common Patterns
Status tables:
| Stage | Status | Branch |
| ----- | --------- | ---------- |
| build | Complete | loom/build |
| test | Executing | loom/test |
Configuration tables:
| Option | Default | Description |
| ---------- | ------- | --------------------- |
| timeout | 300 | Session timeout (sec) |
| auto_merge | false | Enable auto merging |
Right-aligned numbers (script preserves the ---: marker but left-aligns and right-pads the cell text — GFM still renders these right-aligned when displayed):
| Item | Count | Total |
| ----- | ----: | ----: |
| Files | 42 | 500 |
| Lines | 1,234 | 5,000 |
Features
- Aligns each column to its widest cell (separators get a minimum width of 3)
- Single-space padding; cell content is always left-aligned and right-padded (
ljust) regardless of the alignment marker - Preserves the alignment marker in the separator row (
:---,:---:,---:), so GFM rendering still honors it - Uses the header's column count: short body rows gain empty trailing cells and excess body cells are dropped, matching GFM rendering
- Preserves a shared zero-to-three-space Markdown indent and recognizes GFM one-cell body rows without a pipe
- Inserts a blank line before and after each table when missing
Invocation
The script lives in this skill's directory, so pass its path (or copy it to the target dir). allowed-tools permits Bash(python *); invoke via python, not ./.
python /path/to/skills/loom-md-tables/fix-md-tables.py FILE.md # preview to stdout
python /path/to/skills/loom-md-tables/fix-md-tables.py FILE.md -i # -i or --in-place: rewrite
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.
- 6d ago Changed · -37 tokens per session b116da2e73db
- 10d ago First seen · 101 lines · 50 tokens per session scan A b97fa78af373
loom-md-tables is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 856 once invoked, about $0.0001 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
API Discoverability for Agents
Making self-hosted services agent-discoverable — bake in a machine-readable API description (OpenAPI spec or a minimal API.md) when building, and discover-first (spec paths, repo search) before probing when integrating.
Agent Design Principles
A checklist for designing agent personas, skills, and multi-agent pipelines that stay reliable as they grow — grounded in the 12-factor-agents principles.
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.