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.
git clone --depth 1 https://github.com/juanmhidalgo/claude-pluginsWrote 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/commands/juanmhidalgo/claude-plugins/debug)<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/debug"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/debug/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/commands/juanmhidalgo/claude-plugins/debug"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/debug.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 | $0.00031 | $0.01657 |
| Opus 5.5 | $0.00012 | $0.00663 |
| Sonnet 5.5 | $0.00006 | $0.00331 |
| Haiku 4.5 | $0.00003 | $0.00166 |
Grade A, and why
debug scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Start with a failing test at whatever level reaches the bug. If that doesn't fit, see [feedback-loops.md](../skills/debugging-strategies/references/feedback-loops.md) for the other ways to build one (curl script, CLI dif How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Branch: !
git branch --show-current - Recent commits: !
git log --oneline -10
<best_practices> @debug/skills/debugging-strategies/SKILL.md </best_practices>
Systematic Debugging Workflow
Error or failing behavior: $ARGUMENTS
Follow the Stop-the-Line Rule. Do NOT add new features or push past failures.
Step 1: Build a feedback loop (gate)
Everything after this step consumes a feedback loop: one command that goes red on this bug and green once it is fixed. With one, the cause gets found; without one, reading code produces theories, not answers. Spend the effort here.
Start with a failing test at whatever level reaches the bug. If that doesn't fit, see feedback-loops.md for the other ways to build one (curl script, CLI diff, headless browser, replayed capture, bisect harness, differential run) and for flaky and performance bugs.
Exit criterion. Name ONE command that you have already run, and show it with its output (secrets redacted), that is:
- Red-capable: it drives the real code path and asserts the user's exact symptom, not "it didn't crash"
- Deterministic: same verdict every run (for a flaky bug, a pinned and high reproduction rate)
- Fast: seconds, not minutes
- Agent-runnable: it runs without a human clicking. The one exception is a human-run script (way 10 in the reference) when nothing else reaches the bug: say so, and the user's run of it counts as the command
No such command, no Step 2. If you notice yourself reading code to build a theory before it exists, come back here.
If you cannot build one, stop and say so: list what you tried, then ask the user for (a) access to an environment that reproduces it, (b) a redacted captured artifact (HAR file, log dump, request payload), or (c) permission to add temporary instrumentation. During a live incident, mitigation may come before the loop (see /debug:incident).
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 Changed · +25 lines 4a5e6a559b7f
- 1mo ago First seen · 127 lines · 31 tokens per session scan A 0efea248a1eb
debug is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 1,657 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
debug
Command "debug" from JSK9999/ai-nexus, covering /debug, debugging checklist and rules.
dev
Developer tools — debug, commit, PR, code review, refactoring.
fix
Diagnose and fix bugs, errors, and issues in code.
fix
Auto-fix safe Tier-1 issues.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
doctor
Badi configuration validation. Checks all Badi components and produces a diagnostic report.