engineer

An execution agent for approved spreadsheet calculations and Excel workbook changes. It checks the workbook before editing, creates a backup, validates the result, and records an audit event.

In plain words
What is it for?
Use it to carry out an approved spreadsheet editing plan, update specific workbook locations, run calculations, save and reopen the file, and validate the changes.
Why use it?
It reduces accidental changes to unrelated cells and provides checks before and after a workbook is modified. It also gives errors a defined handling and retry process.

Agent

Install

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.

agentmods
npx agentmods add agents/surajpanwar/advanced-calc-engine/engineer
Clone the repo
git clone --depth 1 https://github.com/surajpanwar/advanced-calc-engine
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 176 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00007 $0.00176
Opus 5 $0.00003 $0.00088
Sonnet 5 $0.00001 $0.00035
Haiku 4.5 $0.00001 $0.00018

Measured yesterday against content hash 012514c1496d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

engineer 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 yesterday.

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.

.opencode/agents/engineer.md · 47 lines

What it actually says

Sandbox Engineer

You are the execution agent.

You receive an execution plan from the Sheet Architect.

Responsibilities

  1. Execute approved calculations.
  2. Use the provided Python tools.
  3. Modify only approved workbook locations.
  4. Create backups before modifications.
  5. Verify modifications.
  6. Handle runtime errors.
  7. Retry after diagnosing failures.

Before Modification

Verify:

  • Workbook exists.
  • Worksheet exists.
  • Required columns exist.
  • Target cells exist.
  • Backup has been created.

After Modification

  1. Save workbook.
  2. Reopen workbook.
  3. Verify modifications.
  4. Run validation.
  5. Generate audit event.

Restrictions

Never:

  • Modify unrelated cells.
  • Delete source data without approval.
  • Execute arbitrary user-provided Python.
  • Ignore errors.
Changes

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.

  1. yesterday First seen · 47 lines · 7 tokens per session scan A 012514c1496d

Subscribe to this mod's changes

engineer is an agent published in the GitHub repository surajpanwar/advanced-calc-engine (0 stars, last pushed 17d ago), licensed MIT. It adds 7 tokens to every session and 176 once invoked, about $0.0000 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 2026-08-31.

Related

Other agents, from other repositories

code-reviewer

Idun coding-guideline review against the active rule set.

Idun-Group/idun-agent-platform · 16 tokens

huyen-agents

Updated 2025: This is a summary of Chip Huyen's blog and book chapter on agents, with some added context to provide a comprehensive overview of their design, capabilities, and practical applications.

alirezadir/Agentic-AI-Systems · 0 tokens

policy-analyst

Use when the user asks to analyze policy questions that combine local tabular data with US government sources — jurisdiction comparisons, fiscal-impact analysis, demographic/employment/crime context, or "is policy X working?" questions referencing Census, BLS, FBI Crime Data, or Wikidata. Prefer data-analyst for plain…

dathere/qsv · 77 tokens

data-wrangler

Use when the user asks to clean, transform, reshape, dedupe, join, concatenate, sort, replace, or convert tabular data and produce new output files — e.g., "remove duplicates", "join these two CSVs", "convert to Parquet", "fix encoding". Prefer data-analyst for read-only profiling, statistics, or exploratory queries.

dathere/qsv · 79 tokens

security-reviewer

Use this agent to audit qsv code changes for security issues — unsafe-code misuse, input-validation gaps, command injection, resource exhaustion, and information disclosure. It reports findings with severity, location, and remediation guidance but does NOT apply fixes. Trigger before merging changes to network-facing…

dathere/qsv · 78 tokens

cr-custom-rules

Reviews a supplied diff against explicit repository rules from supplied rule sources. Use only when dispatched by the code-review skill with at least one rule source.

srtab/daiv · 34 tokens