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 Shweta-Mishra-ai/tokenmizer --skill analyzegit clone --depth 1 https://github.com/Shweta-Mishra-ai/tokenmizerWrote 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/shweta-mishra-ai/tokenmizer/analyze)<a href="https://agentmods.dev/skills/shweta-mishra-ai/tokenmizer/analyze"><img src="https://agentmods.dev/badge/skills/shweta-mishra-ai/tokenmizer/analyze/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/shweta-mishra-ai/tokenmizer/analyze"><img src="https://agentmods.dev/badge/skills/shweta-mishra-ai/tokenmizer/analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 10 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00076 | $0.00498 |
| Opus 5 | $0.00038 | $0.00249 |
| Sonnet 5 | $0.00015 | $0.00100 |
| Haiku 4.5 | $0.00008 | $0.00050 |
Grade A, and why
analyze 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.
What it actually says
Analyze a file using TokenMizer's file intelligence layer.
IMPORTANT rule
Never ask the user to paste the file content. Always call TokenMizer to analyze it from the path. Pasting a 50,000-row CSV = 400,000 tokens. TokenMizer reduces it to ~450 tokens.
What to do
Parse $ARGUMENTS:
- First word = file path
- Remaining words = query (what user wants to know)
FILE_PATH=$(echo "$ARGUMENTS" | awk '{print $1}')
QUERY=$(echo "$ARGUMENTS" | cut -d' ' -f2-)
python3 -c "
from tokenmizer.filters.file_intelligence import FileIntelligence
fi = FileIntelligence()
result = fi.process(
open('${FILE_PATH}', 'rb').read(),
'${FILE_PATH}'.split('/')[-1],
token_budget=600,
query='${QUERY}'
)
print(f'File: {result.file_type} | {result.original_tokens:,} → {result.extracted_tokens} tokens ({result.savings_pct:.0f}% saved)')
print()
print(result.content)
"
Token savings by file type
| Type | Typical savings |
|---|---|
| CSV (50k rows) | 99.9% |
| PDF (200 pages) | 98.8% |
| Excel (10 sheets) | 99.7% |
| JSON (1k items) | 95% |
| Code (large file) | 60-80% |
If TokenMizer not installed
pip install "tokenmizer[anthropic]"
Examples of $ARGUMENTS
/data/sales.csv→ analyze with no specific query/data/sales.csv which regions are underperforming→ targeted analysis/reports/Q1.pdf key findings and risks→ relevant page extraction/data/users.xlsx find inactive accounts→ per-sheet analysis
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 · 59 lines · 76 tokens per session scan A 200ddbde5c4a
analyze is a skill published in the GitHub repository Shweta-Mishra-ai/tokenmizer (30 stars, last pushed 23d ago), licensed MIT. It adds 76 tokens to every session and 498 once invoked, about $0.0004 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
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
document-skills
Professional document creation, editing, and analysis for Office formats (docx, pdf, pptx, xlsx). Use when working with Word documents, PDFs, PowerPoint presentations, or Excel spreadsheets.
dev-document
Document generation (PDF, DOCX, XLSX, PPTX). Trigger when the user wants to create a document, generate a report, export to PDF/Word/Excel/PowerPoint, or produce an office file.
sap-docs-extract
Reads a SAP design document (Excel .xlsx, Word .docx, PDF) — or an existing work folder / a raw.txt file — and extracts structured information into separate text files by type: program summary, domains, data elements, tables, error messages, text elements, and process logic. From a document it creates a fresh work…
faostat-analytical-brief
Use when the user wants a short, FAOSTAT-style analytical brief — a multi-page PDF policy document in the FAOSTAT house visual style, with a HIGHLIGHTS box, global/regional/country sections, numbered figures with source lines, explanatory notes, and a data appendix. Use when the user asks for "an analytical brief on…
dokmatiq-docgen
Dokmatiq DocGen skill for Codex, Claude Code, and MCP-enabled AI assistants. Use this skill when the user wants to generate, transform, or analyze documents — including PDF, DOCX, ODT, or Excel/XLSX files — with optional stationery overlay (Briefpapier/letterhead/company letterhead branding applied to generated PDFs).…