Frappe Agent Validator

What it does

When your agent uses it

• Validating Frappe/ERPNext code against best practices and common pitfalls
• Tasks that involve Code review
• Tasks that involve Debugging

Example prompts

• “/frappe-agent-validator”

Requirements

• Python 3
• Compatibility (from SKILL.md): Claude Code, Claude.ai Projects, Claude API. Frappe v14-v16.

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Any import statements? --> FATAL
2. 2Any self. references? --> FATAL (use doc.)
3. 3Any try/except? --> WARNING (usually wrong)
4. 4Uses frappe.throw() for validation? --> GOOD
5. 5Uses doc.field for access? --> GOOD

What it can do on your machine

Read from SKILL.md and the folder at commit 36cfa80. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python and markdown).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Claude Code, Claude.ai Projects, Claude API. Frappe v14-v16.

  From compatibility in the SKILL.md frontmatter.

Context cost

Frappe Agent Validator loads about 2.8k tokens when it runs, and up to ~8.5k if it reads all its reference files. Until then it costs about 130 tokens; SKILL.md has 800 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~130

When it runs · the whole SKILL.md, loaded when a task matches

~2.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~8.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Impertio-Studio/Frappe_Claude_Skill_Package at commit 36cfa80, republished under its MIT licence (© Impertio-Studio). 800 words, ~2,799 tokens.

name

frappe-agent-validator

description

Use when reviewing or validating Frappe/ERPNext code against best practices and common pitfalls. Checks generated code before deployment, validates against all 61 frappe-* skills, catches v16 patterns (extend_doctype_class, type annotations), validates ops patterns (bench commands, deployment), and generates correction reports. Keywords: review code, check script, validate deployment, find bugs, code quality, check my code, is this correct, code review, before deploying, best practices check.

compatibility

Claude Code, Claude.ai Projects, Claude API. Frappe v14-v16.

license

MIT

metadata.author

OpenAEC-Foundation

metadata.version

2.0

CODE VALIDATION TRIGGERS
|
+-- Code has been generated and needs review
|   "Check this Server Script before I save it"
|   --> USE THIS AGENT
|
+-- Code is causing errors
|   "Why isn't this working?"
|   --> USE THIS AGENT
|
+-- Pre-deployment validation
|   "Is this production-ready?"
|   --> USE THIS AGENT
|
+-- Code review for best practices
|   "Can this be improved?"
|   --> USE THIS AGENT
|
+-- Ops/deployment validation
|   "Is my bench setup correct?"
|   --> USE THIS AGENT

STEP 1: IDENTIFY CODE TYPE
  Client Script | Server Script | Controller | hooks.py |
  Jinja | Whitelisted | Bench/Ops | DocType JSON

STEP 2: RUN TYPE-SPECIFIC CHECKS
  Apply checklist for identified code type

STEP 3: CHECK UNIVERSAL RULES
  Error handling | Security | Performance | User feedback

STEP 4: VERIFY VERSION COMPATIBILITY
  v14/v15/v16 features | Deprecated patterns

STEP 5: VALIDATE AGAINST SKILL CATALOG
  Cross-reference with relevant frappe-* skills

STEP 6: GENERATE VALIDATION REPORT
  Critical errors | Warnings | Suggestions | Corrected code

# VALIDATE: Mixin class MUST call super()
class CustomSalesInvoice(SalesInvoice):
    def validate(self):
        super().validate()       # REQUIRED - never skip
        self.custom_validation()

    def on_submit(self):
        super().on_submit()      # REQUIRED - never skip
        self.custom_on_submit()

# v16 recommended pattern
def get_customer_balance(customer: str) -> float:
    ...

# Validate: type hints on public API methods
@frappe.whitelist()
def process_order(order_name: str, action: str = "approve") -> dict:
    ...

# Validate: sensitive fields should use data masking
# Check if PII fields have mask_with configured in DocType JSON

## Code Validation Report

### Code Type: [type]
### Target: [DocType / App / File]
### Event/Trigger: [if applicable]

### CRITICAL ERRORS (Must Fix)
| # | Line | Issue | Fix |
|---|------|-------|-----|

### WARNINGS (Should Fix)
| # | Line | Issue | Recommendation |
|---|------|-------|----------------|

### SUGGESTIONS (Nice to Have)
| # | Line | Suggestion |
|---|------|------------|

### Corrected Code
[If critical errors found, provide corrected version]

### Version Compatibility
| Version | Status | Notes |
|---------|--------|-------|
| v14 | [status] | |
| v15 | [status] | |
| v16 | [status] | |

### Referenced Skills
- frappe-skill-name: [what was validated against]

© Impertio-Studio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in skills/source/agents/frappe-agent-validator of Impertio-Studio/Frappe_Claude_Skill_Package.

• SKILL.md
• references/checklists.md
• references/examples.md
• references/workflow.md

Open the folder on GitHubat commit 36cfa80