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 zapier/gtm-cheat-codes --skill mcp-sheet-cache-bridgegit clone --depth 1 https://github.com/zapier/gtm-cheat-codesWrote 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/zapier/gtm-cheat-codes/mcp-sheet-cache-bridge)<a href="https://agentmods.dev/skills/zapier/gtm-cheat-codes/mcp-sheet-cache-bridge"><img src="https://agentmods.dev/badge/skills/zapier/gtm-cheat-codes/mcp-sheet-cache-bridge.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00764 |
| Opus 5 | $0.00017 | $0.00382 |
| Sonnet 5 | $0.00007 | $0.00153 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
mcp-sheet-cache-bridge 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 8d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Sheet Cache Bridge
Use this skill when a team wants Zapier Tables to be the source of truth but still needs Google Sheets-based tools, scripts, dashboards, or exports to read a simple tab.
What This Skill Does
- Designs a cache tab schema that mirrors only the fields downstream tools need.
- Builds an event-driven sync pattern from the source record store to Google Sheets.
- Uses create, update, and delete logic keyed by a stable record ID.
- Points legacy consumers at the cache instead of direct API reads.
- Documents the field map and cutover plan so the sync stays maintainable.
When You Need This Pattern
- A team replaced a multi-tab spreadsheet with Zapier Tables but still has Apps Script, Looker Studio, formulas, or exports reading Google Sheets.
- A Slack pinned digest or daily report needs fresh rows without running a scheduled full refresh.
- Scheduled syncs would create too many unnecessary tasks.
- Existing tools can read Google Sheets easily but do not have direct access to the source record store.
- The team wants one source of truth with a cheap, stable read path.
Architecture
Zapier Tables source of truth
-> event-driven cache sync on record change
-> Google Sheet cache tab
-> Apps Script, Looker Studio, exports, or digests
Required Connections Through Zapier MCP
- Zapier Tables or another approved record store: read record changes.
- Google Sheets: create, update, and delete cache rows.
- Optional Slack: post digest or sync-health summaries.
Cache Sync Rules
| Source event | Cache action |
|---|---|
| Record matches active cache filter | Create or update matching row |
| Record no longer matches filter | Delete or clear matching row |
| Record deleted in source | Delete matching cache row |
| Cache schema changes | Pause sync until the field map is reviewed |
Cache Tab Columns
| Column | Purpose |
|---|---|
| record_id | Source row ID or external join key |
| display_title | Subject, name, or primary label |
| status | Filter or workflow state |
| priority | Sort order for digest or dashboard |
| assignee | Owner or responsible team |
| link | Source record, ticket, or Slack permalink |
| updated_at | Last sync timestamp |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 87 lines · 34 tokens per session scan A 34380b31d6cb
mcp-sheet-cache-bridge is a skill published in the GitHub repository zapier/gtm-cheat-codes (334 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 764 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 skills, from other repositories
data-report
Turns CSV, Excel, or JSON data into a polished visual report page.
smart-data-collection
A workflow for extracting structured information from images and documents such as PDFs, Word files, and spreadsheets, then storing it in a database.
weekly-crm-report
Cleans a weekly CRM export and produces a regional sales summary. Activates when the user asks to clean a CRM export, deduplicate sales rows, calculate regional totals, or generate a weekly sales report from a CSV.
lark-base
A guide for managing Lark Base, Feishu's spreadsheet-like database and workspace tool. It covers tables, fields, records, views, formulas, forms, dashboards, applications, workflows, and permissions.
liteparse
Parse documents into LLM-ready content entirely on the local machine — PDF / DOCX / XLSX / PPTX / images → Markdown, structured JSON (with bounding boxes), or page screenshots, via the lit CLI. No cloud, no LLM, works offline. Use whenever the user attaches or points to a document that must be read before reasoning…
spreadsheet
Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (.xlsx, .csv, .tsv) with formula-aware workflows, cached recalculation, and visual review.