Agent skill

Debug Ohmycode

by AlphaLab-USTC in AlphaLab-USTC/OhMyCode

Guide for debugging OhMyCode issues. An agent skill from AlphaLab-USTC/OhMyCode.

MITAuto-check passedDevelopment

Install Debug Ohmycode

skills CLI
$ npx skills add AlphaLab-USTC/OhMyCode --skill debug-ohmycode -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AlphaLab-USTC/OhMyCode debug-ohmycode --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AlphaLab-USTC/OhMyCode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/debug-ohmycode .claude/skills/debug-ohmycode && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
debug-ohmycode
GitHub stars
131
Token cost
~1.3k tokens
SKILL.md length
434 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Guide for debugging OhMyCode issues. An agent skill from AlphaLab-USTC/OhMyCode.

  • Works in 4 steps: Check installation: pip3 show ohmycode → Check PATH: which ohmycode && ohmycode… → Reinstall: cd && ./scripts/setup-cli.sh → …
  • User reports errors
  • SKILL.md covers When to Use, Diagnostic Flowchart, Category 1: Installation Issues and Category 2: Provider / API…, plus 5 more sections
  • Calls python3 and pip3

What it does

Debug Ohmycode is an agent skill from AlphaLab-USTC/OhMyCode. Guide for debugging OhMyCode issues. Use when user reports errors, unexpected behavior, or connection problems.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Debugging and LLM cost and token optimization. It works with Microsoft Azure. The repository describes itself as: Minimal and Customizable CC-Style Coding Agent. The licence is MIT.

When your agent uses it

  • User reports errors
  • Unexpected behavior
  • Connection problems

Example prompts

  • “/debug-ohmycode”

Requirements

  • Python 3

Workflow steps

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

  1. Check installation: pip3 show ohmycode
  2. Check PATH: which ohmycode && ohmycode --help
  3. Reinstall: cd && ./scripts/setup-cli.sh
  4. Check Python version: python3 --version (needs 3.9+)

What it can do on your machine

Read from SKILL.md and the folder at commit 4d1bb28. 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:

    • python3
    • pip3

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

  • Network

    No URLs in SKILL.md. Its commands use pip3, which can reach the network depending on how they are called.

    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.

Context cost

Debug Ohmycode loads about 1.3k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 434 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 AlphaLab-USTC/OhMyCode at commit 4d1bb28, republished under its MIT licence (© AlphaLab-USTC). 434 words, ~1,280 tokens.

Download SKILL.mdSave it as .claude/skills/debug-ohmycode/SKILL.md (or your agent's skills folder).
name
debug-ohmycode
description
Guide for debugging OhMyCode issues. Use when user reports errors, unexpected behavior, or connection problems.

Debug OhMyCode

Systematic approach to diagnosing and fixing OhMyCode issues.

When to Use

  • User reports an error or crash
  • Tool calls fail unexpectedly
  • API connection issues
  • Streaming not working
  • Context compression misbehaving
  • Memory or conversation persistence issues

Diagnostic Flowchart

Error? → Which category?
├── "command not found" → Installation Issue
├── API/connection error → Provider Issue
├── Tool execution error → Tool Issue
├── "context compression failed" → Context Issue
├── Memory/resume not working → Storage Issue
└── Unexpected AI behavior → Prompt Issue

Category 1: Installation Issues

Symptoms: ohmycode: command not found, ModuleNotFoundError

Steps:

  1. Check installation: pip3 show ohmycode
  2. Check PATH: which ohmycode && ohmycode --help
  3. Reinstall: cd <project_dir> && ./scripts/setup-cli.sh
  4. Check Python version: python3 --version (needs 3.9+)

Category 2: Provider / API Issues

Symptoms: APIError, AuthenticationError, timeout, empty responses

Steps:

  1. Test API connectivity directly:
python
from openai import OpenAI
client = OpenAI(api_key="...", base_url="...")
r = client.chat.completions.create(
    model="...", messages=[{"role": "user", "content": "hi"}], max_tokens=10
)
print(r.choices[0].message.content)
  1. Check config: cat ~/.ohmycode/config.json

    • Is api_key set?
    • Is base_url correct (trailing /v1)?
    • Is model name correct for this provider?
  2. Check provider registration:

python
from ohmycode.providers.base import PROVIDER_REGISTRY, auto_import_providers
auto_import_providers()
print(list(PROVIDER_REGISTRY.keys()))
  1. Check for rate limiting: look for 429 errors in output. OpenAI provider retries 3 times with [1, 2, 5]s delays.

  2. Azure-specific: verify azure_endpoint and azure_api_version in config.

Category 3: Tool Issues

Symptoms: Tool returns error, wrong output, tool not found

Steps:

  1. Check tool is registered:
python
from ohmycode.tools.base import TOOL_REGISTRY, auto_import_tools
auto_import_tools()
print(list(TOOL_REGISTRY.keys()))
  1. Test tool directly:
python
import asyncio
from ohmycode.tools.base import ToolContext
from ohmycode.tools.<name> import <ToolClass>

ctx = ToolContext(mode="auto", agent_depth=0, cwd=".", is_sub_agent=False)
tool = <ToolClass>()
result = asyncio.run(tool.execute({"param": "value"}, ctx))
print(result.output, result.is_error)
  1. Check permissions: if mode=default, dangerous tools need confirmation. Try --mode auto.

  2. Check concurrent_safe flag: if a tool has side effects but is marked concurrent_safe=True, it may have race conditions when called in parallel.

Category 4: Context / Compression Issues

Symptoms: "Circuit breaker open", conversations getting cut off, AI forgetting context

Steps:

  1. Check token budget in config: token_budget and output_tokens_reserved
  2. Check compression thresholds: ohmycode/core/context.py → maybe_compress()
    • 75% → snip, 80% → micro_compact, 85% → collapse, 90% → auto_compact
  3. Circuit breaker trips after 3 compression failures — usually means the LLM API is down
  4. For tiktoken accuracy issues: counts are approximate (5-15% off for non-OpenAI models)

Quick fix: Increase token_budget in config, or start a new conversation.

Show full SKILL.md (151 more words)Show less

Category 5: Storage Issues

Symptoms: --resume not working, memories not saving, conversations lost

Steps:

  1. Check directories exist:
bash
ls -la ~/.ohmycode/conversations/
ls -la ~/.ohmycode/memory/
  1. Check conversation files: cat ~/.ohmycode/conversations/<latest>.json | python3 -m json.tool | head

  2. Memory index: cat ~/.ohmycode/memory/MEMORY.md

  3. Resume matching: --resume with no argument loads the most recent file by modification time. With an argument, it matches filename substring.

Category 6: Prompt / Behavior Issues

Symptoms: AI ignores instructions, wrong persona, missing tools in responses

Steps:

  1. Check what system prompt is built:
python
from ohmycode.core.system_prompt import build_system_prompt, find_project_instructions
from ohmycode.tools.base import auto_import_tools
auto_import_tools()
prompt = build_system_prompt(mode="auto", cwd=".")
print(prompt)
  1. Check if OHMYCODE.md / CLAUDE.md is being found:
python
from ohmycode.core.system_prompt import find_project_instructions
print(find_project_instructions("."))
  1. Check memory content: cat ~/.ohmycode/memory/MEMORY.md

  2. Check system_prompt_append in config

General Debugging Tips

  • Add --mode auto to skip permission prompts during debugging
  • Keep CLI-first workflow: run with ohmycode only
  • Check python3 -m pytest tests/ -v to verify nothing is broken
  • Read the error traceback bottom-up: the last frame is usually the cause
  • For async issues: look for "RuntimeError: Event loop" — usually means mixing sync/async

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

Files

Just SKILL.md in .agents/skills/debug-ohmycode of AlphaLab-USTC/OhMyCode.

Open the folder on GitHubat commit 4d1bb28

Compare with similar skills

Debug Ohmycode next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Debug Ohmycode compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Debug Ohmycode this skillAlphaLab-USTC/OhMyCode131—~1.3kAutomated safety check: PassMIT
Aspiremicrosoft/aspire.dev1964 repos~1.1kAutomated safety check: PassMIT
Adding A Provider API Featurepydantic/pydantic-ai20k—~3.2kAutomated safety check: PassMIT
Dspy Debugging ObservabilityOmidZamani/dspy-skills1241 repos~2.1kAutomated safety check: WarnMIT
Token-Saver Configurationppgranger/token-saver153—~1kAutomated safety check: PassApache-2.0
Langfuse and LLM Gateway LogsKonghaYao/peri223—~4.3kAutomated safety check: NotesApache-2.0

Similar skills

  • Aspire

    microsoft/aspire.dev

    Official

    Orchestrates Aspire distributed applications using the Aspire CLI for running, debugging, and managing distributed apps.

    196 GitHub starsUsed in 4 repos~1.1k tokens
    DevOps & CloudAuto-check passed
  • Adding A Provider API Feature

    pydantic/pydantic-ai

    Official

    Add a new provider API capability (prompt caching, strict/structured tool calling, thinking/reasoning effort, service tier, safety settings, logprobs, etc.) to Pydantic AI.

    20k GitHub stars~3.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Dspy Debugging Observability

    OmidZamani/dspy-skills

    A skill your agent uses for debugging DSPy programs, inspecthistory, tracing LLM calls, custom callbacks, observability, monitoring, and cost tracking.

    124 GitHub starsUsed in 1 repo~2.1k tokens
    DevOps & CloudAuto-check: warnings
  • Token-Saver Configuration

    ppgranger/token-saver

    Checks and tunes token-saver output compression: reads stats, explains why a command was or was not compressed, and edits config files or environment variables.

    153 GitHub stars~1k tokensUpdated 18 days ago
    Agent WorkflowsAuto-check passed
  • Queries Langfuse traces, prompts, datasets and sessions, and analyzes local LLM gateway logs for requests, context growth, token use and cache hits.

    223 GitHub stars~4.3k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes
  • Debug E2E Pipeline

    kubernetes-sigs/cloud-provider-azure

    Official

    Fetch and analyze Prow e2e pipeline failures for cloud-provider-azure.

    294 GitHub stars~3.4k tokensUpdated today
    Testing & QAAuto-check passed

More from AlphaLab-USTC/OhMyCode

All 10 skills in this repo
  • Add Feature

    AlphaLab-USTC/OhMyCode

    Guide for adding a new feature to OhMyCode. An agent skill from AlphaLab-USTC/OhMyCode.

    131 GitHub stars~995 tokensUpdated 6 mo ago
    Auto-check passed
  • Add Provider

    AlphaLab-USTC/OhMyCode

    Guide for adding a new LLM provider to OhMyCode. An agent skill from AlphaLab-USTC/OhMyCode.

    131 GitHub stars~888 tokensUpdated 6 mo ago
    Auto-check passed
  • Add Tool

    AlphaLab-USTC/OhMyCode

    Guide for adding a new tool to OhMyCode. An agent skill from AlphaLab-USTC/OhMyCode.

    131 GitHub stars~758 tokensUpdated 6 mo ago
    Auto-check passed
  • Bench

    AlphaLab-USTC/OhMyCode

    Run OhMyCode benchmarks — score any provider/model with token tracking.

    131 GitHub stars~941 tokensUpdated 6 mo ago
    Auto-check passed
  • Customize Response Style

    AlphaLab-USTC/OhMyCode

    Guide for customizing OhMyCode's terminal output style and rendering.

    131 GitHub stars~1.1k tokensUpdated 6 mo ago
    Auto-check passed
  • Customize System Prompt

    AlphaLab-USTC/OhMyCode

    Guide for customizing OhMyCode's AI personality and behavior via system prompt.

    131 GitHub stars~819 tokensUpdated 6 mo ago
    Auto-check passed

Works with

Categories

Questions about Debug Ohmycode

What does Debug Ohmycode do?

Guide for debugging OhMyCode issues. An agent skill from AlphaLab-USTC/OhMyCode. Debug Ohmycode is an agent skill from AlphaLab-USTC/OhMyCode. Guide for debugging OhMyCode issues.

When should I use Debug Ohmycode?

Debug Ohmycode fits situations like: user reports errors; unexpected behavior; connection problems.

How do I install Debug Ohmycode in Claude Code?

Run `npx skills add AlphaLab-USTC/OhMyCode --skill debug-ohmycode -a claude-code`. Or copy the skill folder (.agents/skills/debug-ohmycode in AlphaLab-USTC/OhMyCode) into .claude/skills/debug-ohmycode in your project. Claude Code loads it when a task matches its description.

How do I install Debug Ohmycode in Codex?

Run `npx skills add AlphaLab-USTC/OhMyCode --skill debug-ohmycode -a codex`. Or copy the skill folder (.agents/skills/debug-ohmycode in AlphaLab-USTC/OhMyCode) into .agents/skills/debug-ohmycode in your project. Codex loads it when a task matches its description.

Can I use Debug Ohmycode in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AlphaLab-USTC/OhMyCode --skill debug-ohmycode -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/debug-ohmycode, .gemini/skills/debug-ohmycode, .github/skills/debug-ohmycode and .opencode/skills/debug-ohmycode in your project.

What does Debug Ohmycode need to run?

Going by SKILL.md and its folder, Debug Ohmycode needs the command-line tools its instructions call (python3 and pip3). Our summary lists: Python 3.

Does Debug Ohmycode access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Debug Ohmycode safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Debug Ohmycode use?

Debug Ohmycode is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Debug Ohmycode use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Debug Ohmycode?

Skills that share tags, products or a category with Debug Ohmycode: Aspire (microsoft/aspire.dev, 196 stars), Adding A Provider API Feature (pydantic/pydantic-ai, 20k stars), Dspy Debugging Observability (OmidZamani/dspy-skills, 124 stars) and Token-Saver Configuration (ppgranger/token-saver, 153 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Debug Ohmycode?

AlphaLab-USTC (a GitHub user) maintains it in AlphaLab-USTC/OhMyCode, which has 131 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on April 2, 2026.

Source: AlphaLab-USTC/OhMyCode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.