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 commands/saigonxiii/evc/export-cleangit clone --depth 1 https://github.com/SaigonXIII/evcWhat 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 | $0.00032 | $0.00539 |
| Opus 5 | $0.00016 | $0.00269 |
| Sonnet 5 | $0.00006 | $0.00108 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
export-clean 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 2d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Export Clean
Produce a clean, public-ready copy of a staging HTML file with all internal review artifacts stripped. Removes version drawers, internal annotations, and any element marked data-internal.
Usage
/project:export-clean staging/blog/[slug]-blog.html
/project:export-clean staging/dashboards/weekly-report.html [output-path]
When to Use
- Before sharing a staging page with an external reviewer
- Before uploading staging HTML as public documentation
- Before
/blog-publish(auto-called, but can be run manually to inspect output) - Before taking a public screenshot of a staging page
Steps
1. Resolve input and output paths
- Input: first arg, must be an existing file in
staging/ - Output: second arg, or defaults to
staging/exports/[same-filename]
2. Run the export script
scripts/export-staging.sh [input] [output]
The script:
- Removes every element with
data-internal="..."attribute - Strips CSS rules for
.version-drawer,.vd-toggle,.vd-label,.vd-body,.vd-hint - Removes any
<link>toversion-drawer.css - Collapses orphaned blank lines
3. Verify output
Check the output file:
- Does not contain
data-internal - Does not contain
version-drawer - File size is reasonable (smaller than input but not empty)
- HTML structure intact (has
<html>,<body>)
4. Report
EXPORT CLEAN
════════════════════════════════════════
Input: [input-path]
Output: [output-path]
Removed: [N] internal elements
Size: [input-kb]KB → [output-kb]KB
Preview: open [output-path]
════════════════════════════════════════
Rules
- Never modify the input file — always write a new output
- If output path already exists, prompt before overwriting
- Never strip elements without
data-internal— this command is specifically for marked elements - The script is pure-Python regex-based; it does NOT use a full HTML parser. Nested
data-internalelements are not supported (avoid them).
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.
- 2d ago First seen · 74 lines · 32 tokens per session scan A 6e9df8e56f0b
export-clean is a command published in the GitHub repository SaigonXIII/evc (56 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 539 once invoked, about $0.0002 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 commands, from other repositories
review-tool
Research a tool or product for skill-gap, architecture, and verb-fit per the Anatomy framework.
setup
First-run setup — replace the fictional company and authors with yours.
review-content
Review content for brand alignment, lead placement, bio consistency, and proof points.
voice-check
Check a draft against the author's voice profile and flag deviations.
content-status
Scan all content directories and report status of drafts, ideas, and published content.
draft-blog
Scaffold a blog post with proper structure, voice, and frontmatter.