Frappe Agent Debugger

What it does

When your agent uses it

• Debugging Frappe errors
• Using bench console for live inspection
• Analyzing tracebacks
• Reading Frappe log files

Example prompts

• “/frappe-agent-debugger”

Requirements

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

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Error Classification
2. 2Mechanism Identification
3. 3File Path Conventions
4. 4Diagnosis Checklists (Quick Reference)

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

  Shell commands in SKILL.md call:

  • python

  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 Debugger loads about 2.9k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 182 tokens; SKILL.md has 731 words of instructions outside code blocks.

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

~182

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

~2.9k

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

~10k

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). 731 words, ~2,855 tokens.

name

frappe-agent-debugger

description

Use when debugging Frappe errors, using bench console for live inspection, analyzing tracebacks, or reading Frappe log files. Prevents wasted debugging time from ignoring log context, misreading tracebacks, and not using bench console effectively. Covers bench console, frappe.logger, error log DocType, traceback analysis, common error patterns, log file locations, pdb/debugger integration, VS Code DAP, profiling, Frappe Recorder, mariadb diagnostics. Keywords: debug, bench console, traceback, error log, frappe.logger, pdb, debugging, log analysis, inspect, VS Code, DAP, profiling, recorder, mariadb, monitor, ERPNext error, how to debug, find the bug, what went wrong, stack trace, error message..

compatibility

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

license

MIT

metadata.author

OpenAEC-Foundation

metadata.version

2.0

ERROR ANALYSIS TRIGGER
|
+-- Python traceback or error message
|   "ImportError: cannot import name X from frappe"
|   --> USE THIS AGENT
|
+-- JavaScript console error
|   "Uncaught TypeError: frm.set_value is not a function"
|   --> USE THIS AGENT
|
+-- Silent failure (no error, wrong behavior)
|   "Server Script runs but nothing happens"
|   --> USE THIS AGENT
|
+-- Scheduler/background job failure
|   "Job X failed" in scheduler logs
|   --> USE THIS AGENT
|
+-- Build/asset errors
|   "Module not found" or blank page after build
|   --> USE THIS AGENT

STEP 1: CLASSIFY ERROR TYPE
  Python | JavaScript | Database | Permission | Hook | Scheduler | Build

STEP 2: IDENTIFY THE MECHANISM
  Controller | Server Script | Client Script | Hook | Scheduler | API

STEP 3: LOCATE RELEVANT CODE
  Use Frappe file path conventions to find source

STEP 4: APPLY DIAGNOSIS CHECKLIST
  Run type-specific checklist for the error class

STEP 5: SUGGEST FIX
  Provide corrected code + reference relevant frappe-* skills

bench --site {site} console
# Then:
frappe.get_doc("Sales Invoice", "SINV-00001")  # Inspect document
frappe.db.sql("SELECT name FROM `tabSales Invoice` LIMIT 5")  # Raw SQL
frappe.get_hooks("doc_events")  # Inspect active hooks
frappe.get_all("Server Script", filters={"disabled": 0}, fields=["name", "script_type"])

bench --site {site} mariadb
-- Then:
SHOW CREATE TABLE `tabSales Invoice`;
SELECT * FROM `tabError Log` ORDER BY creation DESC LIMIT 10;

bench doctor  # Check scheduler, workers, background jobs

logger = frappe.logger("my_debug", allow_site=True)
logger.info(f"Variable value: {my_var}")
# Logs to: sites/{site}/logs/my_debug.log

Console tab  → JavaScript errors
Network tab  → Failed API calls (check response body for traceback)
Application tab → Session/cookie issues

## Debug Report

### Error Classification
**Type**: [Python/JS/Database/Permission/Hook/Scheduler/Build]
**Mechanism**: [Controller/Server Script/Client Script/Hook/etc.]

### Root Cause
[One-sentence diagnosis]

### Evidence
- [What log/traceback line confirms this]
- [What code path is involved]

### Fix
[Corrected code or configuration change]

### Verification Steps
1. [How to confirm the fix works]
2. [What to check in logs/UI]

### Referenced Skills
- `frappe-*`: [what was consulted]

ERROR RECEIVED
|
+-- Has traceback?
|   +-- YES: Read LAST line first (actual error)
|   |   +-- Contains ".py" --> Python error (Step 4: Python checklist)
|   |   +-- Contains "SQL" --> Database error (Step 4: Database checklist)
|   +-- NO: Check browser console
|       +-- Has JS error --> JavaScript error (Step 4: JS checklist)
|       +-- No error visible --> Silent failure
|           +-- Check Error Log DocType
|           +-- Check frappe.log
|           +-- Add frappe.logger() statements
|
+-- Error after bench command?
|   +-- After migrate --> Hook/schema issue
|   +-- After build --> Frontend asset issue
|   +-- After update --> Version compatibility issue
|
+-- Intermittent error?
    +-- Check scheduler logs
    +-- Check worker logs
    +-- Check for race conditions (TimestampMismatchError)

© 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 5 other files (references) in skills/source/agents/frappe-agent-debugger of Impertio-Studio/Frappe_Claude_Skill_Package.

• SKILL.md
• references/.gitkeep
• references/advanced-debugging.md
• references/checklists.md
• references/examples.md
• references/workflow.md

Open the folder on GitHubat commit 36cfa80