Atlas / Skills / jeremylongshore / Fondo Performance Tuning

Fondo Performance TuningSAFE

skills/jeremylongshore/fondo-performance-tuning

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
1.6.0
Hosts
1 documented
License
MIT
Stars
2,822
01

Overview

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Read from source at commit 4f83675ca38aOBSERVED · 2026-10-08
02

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-codementioned
03

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: fondo-performance-tuning
description: 'Optimize Fondo workflows including faster month-end close, efficient

  data exports, and streamlined CPA communication.

  Trigger: "fondo performance", "fondo faster close", "optimize fondo workflow".

  '
allowed-tools: Read, Write, Edit, Grep
version: 1.6.0
license: MIT
author: Jeremy Longshore <[email protected]>
tags:
- saas
- accounting
- fondo
compatibility: Designed for Claude Code
---
# Fondo Performance Tuning

## Overview

Speed up Fondo workflows: faster month-end close (target: 15 days), reduced back-and-forth with CPA team, and efficient data export processing.

## Prerequisites

- A named finance owner, approved close calendar, data-access policy, and aggregate baseline for close time and exception volume.
- Synthetic/sample data for workflow tests; real financial records remain in the approved accounting environment.

## Output

Produce an operational receipt with period, aggregate bottleneck metrics, approved workflow change, owner, verification date, and unresolved exceptions. Do not include account numbers, transactions, tax documents, or credentials.

## Error Handling

- Pause automation when an import, categorization, or reconciliation result is incomplete or unexpected; route it to the finance owner.
- Do not replace professional review with an automated classification or calculator result.
- Redact all financial data in performance diagnostics and roll back changes that harm accuracy or auditability.

## Examples

Use a fictional month of aggregate expenses to test a categorization workflow. Compare only close duration and exception count, then have the authorized finance reviewer approve the result before changing a live process.

## Instructions

### Faster Month-End Close

| Bottleneck | Current | Target | How |
|------------|---------|--------|-----|
| Uncategorized transactions | 3-5 days wait | Same day | Set up auto-categorization rules |
| CPA questions | 2-3 day response | 1 day | Batch-answer in single session |
| Missing receipts | 5+ days | 0 days | Use Brex/Ramp auto-receipt capture |
| Bank reconciliation | 2 days | Automated | Ensure Plaid connection is stable |

### Auto-Categorization Rules

```
Dashboard > Settings > Categorization Rules

Examples:
  "AWS" → Cloud Infrastructure (R&D)
  "GitHub" → Software Tools (R&D)
  "Gusto" → Payroll
  "WeWork" → Office/Rent
  "United Airlines" → Travel
  "Uber Eats" → Meals (50% deductible)
```

### Batch CPA Communication

Instead of replying to each question individually:

1. Set aside 30 minutes weekly (e.g., Monday AM)
2. Open Dashboard > Messages > Open Items
3. Answer all outstanding questions in one session
4. This reduces close time by 3-5 days

### Efficient Data Exports

```typescript
// Cache Fondo exports to avoid repeated downloads
const CACHE_DIR = '.cache/fondo';
const CACHE_TTL = 24 * 60 * 60 * 1000;  // 24 hours

async function getCachedExport(reportType: string, dateRange: string) {
  const cacheKey = `${reportType}-${dateRange}.csv`;
  const cachePath = `${CACHE_DIR}/${cacheKey}`;

  if (fs.existsSync(cachePath)) {
    const stat = fs.statSync(cachePath);
    if (Date.now() - stat.mtimeMs < CACHE_TTL) {
      return fs.readFileSync(cachePath, 'utf-8');
    }
  }
  // Download fresh from Dashboard > Reports > Export
  console.log(`Cache miss: download ${reportType} for ${dateRange} from Fondo Dashboard`);
  return null;
}
```

## Resources

- Fondo Dashboard

## Next Steps

For cost optimization, see `fondo-cost-tuning`.
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 4f83675ca38afull audit observations/trust-audit/skill/jeremylongshore__fondo-performance-tuning.json · Report an issue / request a re-scan
05

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-084f83675ca38aSAFEB89first audit
06

Questions

What does the Fondo Performance Tuning skill do?

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Is Fondo Performance Tuning safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can Fondo Performance Tuning access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

Which assistants does Fondo Performance Tuning work with?

Its documentation mentions claude-code. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (4f83675ca38a), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement