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/intellegix/intellegix-code-agent-toolkit/spreadsheet-auditgit clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkitWhat 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 | $0.00000 | $0.07845 |
| Opus 5 | $0.00000 | $0.03922 |
| Sonnet 5 | $0.00000 | $0.01569 |
| Haiku 4.5 | $0.00000 | $0.00784 |
Grade A, and why
spreadsheet-audit 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 — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spreadsheet-audit — Comprehensive Excel Spreadsheet Audit
Perform a 6-step audit of an Excel spreadsheet for formula correctness, formatting consistency, data integrity, boss-auditable simplicity, and spec compliance. Uses the excel-screenshot MCP server tools — no Excel installation required.
Architecture: Validate → Discover → Load Specs → Deep Audit (5 categories) → Visual Verify → Report. Free, fully local.
BOSS-AUDITABLE PRINCIPLE: Every formula in the workbook must be understandable by a non-technical person who clicks the cell. Only simple arithmetic (+, -, *, /), plain cell references, and small SUM() are allowed. Time entry totals must show each individual entry as an explicit addend (=8+8+8, never =SUM(range) or =24). This rule is enforced in Step 3E and cross-checked in Steps 3A and 3D.
CRITICAL: Execute the full audit silently and present results at the end. Only interact with the user in Step 0 (file selection) and Step 2 (spec clarification if no specs found).
Input
$ARGUMENTS = path to .xlsx file (required), optionally followed by sheet name(s) or --focus flag.
Examples:
- /spreadsheet-audit "C:\path\to\budget.xlsx"
- /spreadsheet-audit "C:\path\to\report.xlsx" Sheet1
- /spreadsheet-audit "C:\path\to\data.xlsx" --focus formulas
Step 0: Validate Input — MANDATORY, SILENT
- Parse
$ARGUMENTSfor file path (first argument = file path, remaining = sheet names or--focusflag) - If no path provided:
Globfor **/*.xlsx in working directory- If exactly 1 found → use it (confirm with user)
- If 0 found → STOP: "No .xlsx files found. Provide a path."
- If 2+ found → use
AskUserQuestionto ask user to pick one (list all found)
- Verify file exists and is readable by calling spreadsheet_list_sheets(file_path)
- If file is locked (PermissionError): report "Close Excel first, then retry"
- If file is password-protected (InvalidFileException): STOP: "File is password-protected. Remove protection first."
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 · 456 lines · 0 tokens per session scan A 5940c6d45b3a
spreadsheet-audit is a command published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,845 tokens. 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
README
Git workflow and quality assurance commands for the claude-skills repository.
portaljs-check-data-quality
Audit a local or remote tabular file (CSV/TSV) for common data quality issues. Read-only. Use only when the user explicitly asks to check or audit data quality.
agentlas-cloud
Staff a task only from the signed-in owner's Agent Cloud agents.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
tldr
Re-apply TLDR rules for this turn (verdict first, no filler).
me-figure-discussion
Write or review thermal-fluid figure discussion with observation, physical mechanism, comparison, uncertainty, and claim limits.