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 agentmods add skills/alphalab-ustc/ohmycode/debug-ohmycodenpx skills add AlphaLab-USTC/OhMyCode --skill debug-ohmycodegit clone --depth 1 https://github.com/AlphaLab-USTC/OhMyCodeWhat 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 | $0.00026 | $0.01286 |
| Opus 5 | $0.00013 | $0.00643 |
| Sonnet 5 | $0.00005 | $0.00257 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
debug-ohmycode 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 2d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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:
- Check installation:
pip3 show ohmycode - Check PATH:
which ohmycode && ohmycode --help - Reinstall:
cd <project_dir> && ./scripts/setup-cli.sh - Check Python version:
python3 --version(needs 3.9+)
Category 2: Provider / API Issues
Symptoms: APIError, AuthenticationError, timeout, empty responses
Steps:
- Test API connectivity directly:
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)
-
Check config:
cat ~/.ohmycode/config.json- Is
api_keyset? - Is
base_urlcorrect (trailing/v1)? - Is
modelname correct for this provider?
- Is
-
Check provider registration:
from ohmycode.providers.base import PROVIDER_REGISTRY, auto_import_providers
auto_import_providers()
print(list(PROVIDER_REGISTRY.keys()))
-
Check for rate limiting: look for 429 errors in output. OpenAI provider retries 3 times with [1, 2, 5]s delays.
-
Azure-specific: verify
azure_endpointandazure_api_versionin config.
Category 3: Tool Issues
Symptoms: Tool returns error, wrong output, tool not found
Steps:
- Check tool is registered:
from ohmycode.tools.base import TOOL_REGISTRY, auto_import_tools
auto_import_tools()
print(list(TOOL_REGISTRY.keys()))
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.
- 2d ago First seen · 161 lines · 26 tokens per session scan A 1258ca11164c
debug-ohmycode is a skill published in the GitHub repository AlphaLab-USTC/OhMyCode (131 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 1,286 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…