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 commands/rohitg00/awesome-claude-code-toolkit/debuggit clone --depth 1 https://github.com/rohitg00/awesome-claude-code-toolkitWhat 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 | $0.00000 | $0.00335 |
| Opus 5 | $0.00000 | $0.00168 |
| Sonnet 5 | $0.00000 | $0.00067 |
| Haiku 4.5 | $0.00000 | $0.00034 |
Grade A, and why
debug 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 yesterday.
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.
What it actually says
Systematically debug an issue by analyzing symptoms, forming hypotheses, and testing them.
Steps
- Gather the bug report: error message, stack trace, reproduction steps, expected vs actual behavior.
- Identify the entry point where the issue manifests (endpoint, UI action, CLI command).
- Trace the execution path from entry to error:
- Read the code path that handles the triggering action.
- Check for recent changes in the affected files:
git log --oneline -10 -- <file>. - Look for related error handling or edge cases.
- Form hypotheses ranked by likelihood:
- Data issue: unexpected null, wrong type, missing field.
- Logic error: incorrect condition, off-by-one, wrong operator.
- State issue: race condition, stale cache, missing initialization.
- Environment: missing config, version mismatch, network failure.
- Test each hypothesis:
- Add targeted logging or breakpoints.
- Write a minimal reproduction test case.
- Check edge cases around the failure point.
- Implement the fix and verify it resolves the issue.
- Add a regression test that would catch the bug if reintroduced.
Format
Bug: <description>
Root Cause: <what actually went wrong>
Fix: <what was changed>
Files: <list of modified files>
Test: <regression test added>
Rules
- Start with the simplest hypothesis before investigating complex causes.
- Never fix a bug without understanding the root cause.
- Always add a regression test for the fix.
- Check if the same bug pattern exists elsewhere in the codebase.
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.
- yesterday First seen · 39 lines · 0 tokens per session scan A 899155c50712
debug is a command published in the GitHub repository rohitg00/awesome-claude-code-toolkit (2,570 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 335 tokens. 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 commands, from other repositories
create-prompt
Create a new prompt that another Claude can execute.
create-slash-command
Create a new slash command following best practices and patterns.
design
Command "design" from laborany/laborany, covering /ppt-design 命令 - 风格设计, 命令说明, 触发方式, 执行流程 and step 1: 展示风格选择菜单.
brainstorm
You are a Solution Brainstormer, an elite software engineering expert who specializes in system architecture design and technical decision-making. Your core mission is to collaborate with users to find the best possible solutions while maintaining brutal honesty about feasibility and trade-offs.
scout
Scout given directories to respond to the user's requests.
enhance
Analyze the current copy issues and enhance it.