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 richardcb/oh-my-gemini --skill debug-assistantgit clone --depth 1 https://github.com/richardcb/oh-my-geminiWrote 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/richardcb/oh-my-gemini/debug-assistant)<a href="https://agentmods.dev/skills/richardcb/oh-my-gemini/debug-assistant"><img src="https://agentmods.dev/badge/skills/richardcb/oh-my-gemini/debug-assistant.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.01690 |
| Opus 5 | $0.00019 | $0.00845 |
| Sonnet 5 | $0.00008 | $0.00338 |
| Haiku 4.5 | $0.00004 | $0.00169 |
Grade A, and why
debug-assistant 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 7d 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Assistant Skill
Goal
Provide systematic debugging support through structured analysis, hypothesis generation, and methodical testing to identify and fix bugs efficiently.
Activation Triggers
- User reports an error or bug
- User says "debug", "fix this error", "why isn't this working"
- Test failures need investigation
- Unexpected behavior reported
Debugging Framework
1. Gather Information
# Get error context
echo "=== Recent Error Logs ==="
tail -50 *.log 2>/dev/null || echo "No log files"
# Check test output
echo "=== Test Failures ==="
npm test 2>&1 | tail -50 || echo "No test command"
# Check TypeScript errors
echo "=== Type Errors ==="
npm run typecheck 2>&1 | tail -30 || tsc --noEmit 2>&1 | tail -30 || echo "No typecheck"
# Check runtime errors
echo "=== Console Errors ==="
# User needs to provide these
2. Reproduce the Bug
Questions to ask:
- What is the expected behavior?
- What is the actual behavior?
- What are the exact steps to reproduce?
- When did this start happening?
- What changed recently?
Reproduction checklist:
# Check recent changes
git log --oneline -10
# Check what files changed
git diff HEAD~5 --name-only
# Check if it reproduces in a fresh state
npm ci && npm run build && npm test
3. Form Hypotheses
Based on the error, generate possible causes:
| Symptom | Possible Causes |
|---|---|
TypeError: undefined |
Missing null check, async timing, wrong import |
Network error |
API down, wrong URL, CORS, auth expired |
Test timeout |
Infinite loop, missing async/await, slow DB |
Build failure |
Type mismatch, missing dependency, syntax error |
Runtime crash |
Memory leak, stack overflow, unhandled promise |
4. Investigate Systematically
For Each Hypothesis:
A. Identify relevant code
# Find files related to the error
grep -rn "errorKeyword" src/ --include="*.ts" | head -20
# Find function definitions
grep -rn "functionName" src/ --include="*.ts" | head -10
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.
- 7d ago First seen · 285 lines · 39 tokens per session scan A 3d425ec76187
debug-assistant is a skill published in the GitHub repository richardcb/oh-my-gemini (16 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 1,690 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 2026-08-30.
Other skills, from other repositories
canary-watch
Post-deploy monitoring and canary health verification.
benchmark
Performance baseline measurement and regression detection.
troubleshooter
Specialized in system-wide troubleshooting using metrics and logs.
click-path-audit
Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI in an inconsistent state. Use when: systematic debugging found no bugs but users report broken buttons, or after any…
plankton-code-quality
Write-time code quality enforcement using Plankton — auto-formatting, linting, and AI-powered fixes on every file edit via hooks.
evm-token-decimals
Prevent silent decimal mismatch bugs across EVM chains. Covers runtime decimal lookup, chain-aware caching, bridged-token precision drift, and safe normalization for bots, dashboards, and DeFi tools.