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 skills add latestaiagents/agent-skills --skill debug-with-aigit clone --depth 1 https://github.com/latestaiagents/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/latestaiagents/agent-skills/debug-with-ai)<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/debug-with-ai"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/debug-with-ai/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/debug-with-ai"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/debug-with-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00049 | $0.01660 |
| Opus 5 | $0.00024 | $0.00830 |
| Sonnet 5 | $0.00010 | $0.00332 |
| Haiku 4.5 | $0.00005 | $0.00166 |
Grade A, and why
debug-with-ai 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 8d 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug with AI
Structured debugging workflows using AI as your debugging partner.
When to Use
- Code throws an error you don't understand
- Feature works sometimes but not always
- Unexpected behavior that's hard to trace
- Performance issues or memory leaks
- Complex stack traces to decipher
The Debugging Framework
┌───────────────────────────────────────────┐
│ 1. REPRODUCE - Can you trigger it? │
├───────────────────────────────────────────┤
│ 2. ISOLATE - Where exactly is the issue? │
├───────────────────────────────────────────┤
│ 3. UNDERSTAND - Why does it happen? │
├───────────────────────────────────────────┤
│ 4. FIX - Make minimal change to resolve │
├───────────────────────────────────────────┤
│ 5. VERIFY - Confirm fix, add test │
└───────────────────────────────────────────┘
Step 1: Reproduce
Before asking AI for help, gather information:
Collect This Information
## Bug Report
**What I expected:**
[Expected behavior]
**What actually happened:**
[Actual behavior]
**Error message (if any):**
[Full error message and stack trace]
**Steps to reproduce:**
1. [Step 1]
2. [Step 2]
3. [Step 3]
**Environment:**
- Node/Browser version:
- OS:
- Relevant packages:
**Code involved:**
```[paste relevant code]```
**What I've already tried:**
- [Attempt 1]
- [Attempt 2]
Step 2: Isolate
Binary Search for Bugs
If you don't know where the bug is:
- Comment out half the code
- Does bug still occur?
- Yes → Bug is in remaining code
- No → Bug is in commented code
- Repeat with that half
AI Prompt for Isolation
I have a bug somewhere in this code flow:
1. Function A calls Function B
2. Function B processes data and calls Function C
3. Function C returns result
The bug manifests as [description].
Here's the code:
```[paste relevant functions]```
Help me identify which function is most likely causing the issue
and what I should check first.
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.
- 8d ago First seen · 336 lines · 49 tokens per session scan A bc987260baea
debug-with-ai is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 1,660 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
ai-critique
A general diagnosis assistant for product, operations, technical, and software work. It analyzes supplied material and produces a summary, conclusions, action suggestions, and reusable deliverables.
ai-equipment-failure-rca-draft
A root-cause analysis draft assistant for investigating equipment failures. Root-cause analysis means looking for the underlying reason a failure happened, not only its visible symptom.
ai-performance
A performance diagnosis assistant for finding what may be slowing a service or product down.
ai-quality-complaint-8d-report
A business-diagnosis assistant for creating or reviewing an 8D report. An 8D report is a structured method for investigating a quality problem and documenting corrective action.
langsmith-tracing
LangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for LangChain/LangGraph agents.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.