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 mazumba/opencode-dockerized --skill excelgit clone --depth 1 https://github.com/mazumba/opencode-dockerizedWrote 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/mazumba/opencode-dockerized/excel)<a href="https://agentmods.dev/skills/mazumba/opencode-dockerized/excel"><img src="https://agentmods.dev/badge/skills/mazumba/opencode-dockerized/excel/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/mazumba/opencode-dockerized/excel"><img src="https://agentmods.dev/badge/skills/mazumba/opencode-dockerized/excel.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00038 | $0.00523 |
| Opus 5.5 | $0.00015 | $0.00209 |
| Sonnet 5.5 | $0.00008 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
excel 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 15d 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
The container has openpyxl 3.0.9 from Debian (import openpyxl). There is no LibreOffice, no xlrd and no Excel, so nothing can recalculate formulas or open legacy files.
Formulas
- openpyxl stores formulas as strings and never evaluates them.
load_workbook(p)returns the formula text ("=A2+B2").load_workbook(p, data_only=True)returns the value Excel last cached when it saved the file.- A file written by openpyxl has no cached values, so reading it back with
data_only=TruegivesNone. If you need the numbers, compute them in Python. Write the formula as well when the user expects a live sheet. - Never save a workbook that was loaded with
data_only=True. Saving replaces every formula with its cached value.
Editing an existing file
- Save to a new path, and overwrite the original only when the user asks. Loading and saving drops what openpyxl cannot model: shapes, form controls, slicers, and external-link caches. Macros are dropped too, unless the file is
.xlsmloaded withkeep_vba=True. .xlsraisesInvalidFileException. Ask the user to re-save it as.xlsx.
Reading data
- For large files, use
load_workbook(p, read_only=True)withws.iter_rows(values_only=True), thenwb.close(). For large writes, useWorkbook(write_only=True)andws.append(row). - Dates read back as
datetime, even for date-only cells. Whether a cell displays as a date, percent or currency depends only oncell.number_format("yyyy-mm-dd","0.00%",'#,##0.00 "€"'). - A merged range keeps its value in the top-left cell. The other cells read as
None. ws.max_rowandws.max_columncount formatted empty cells too, so find the real data extent by scanning.
Layout
Column widths are not automatic: set ws.column_dimensions["A"].width. Freeze the header row with ws.freeze_panes = "A2".
Verify by reloading the saved file and printing the cells you changed.
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.
- 15d ago First seen · 32 lines · 38 tokens per session scan A 6518ee80c6c7
excel is a skill published in the GitHub repository mazumba/opencode-dockerized (6 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 523 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-24.
excel compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| excelmazumba/opencode-dockerized | Skill | 6 | 2d ago | MIT | A | 38 | Claude Code, Codex |
| dcf-modelNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 14 | Claude Code, Codex |
| gogopenclaw/openclaw | Skill | 394k | today | MIT | A | 20 | Claude Code, Codex |
| xlsxasgeirtj/system_prompts_leaks | Skill | 71k | yesterday | CC0-1.0 | A | 206 | Claude Code, Codex |
| audit-xlsanthropics/financial-services | Skill | 41k | 10d ago | Apache-2.0 | A | 104 | Claude Code |
| artifact-template-analytics-dashboardasgeirtj/system_prompts_leaks | Skill | 71k | yesterday | CC0-1.0 | A | 47 | Claude Code, Codex |
| google-drive-sheetsyc-software/qm | Skill | 16k | today | MIT | A | 32 | Claude Code, Codex |