Borrowing it
Nothing to install: this file belongs to tiagosilva07/zyrax-guard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tiagosilva07/zyrax-guard/main/.claude/agents/debugger.mdgit clone --depth 1 https://github.com/tiagosilva07/zyrax-guardWrote 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/agents/tiagosilva07/zyrax-guard/debugger)<a href="https://agentmods.dev/agents/tiagosilva07/zyrax-guard/debugger"><img src="https://agentmods.dev/badge/agents/tiagosilva07/zyrax-guard/debugger/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/agents/tiagosilva07/zyrax-guard/debugger"><img src="https://agentmods.dev/badge/agents/tiagosilva07/zyrax-guard/debugger.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 | $0.00092 | $0.00594 |
| Opus 5.5 | $0.00037 | $0.00238 |
| Sonnet 5.5 | $0.00018 | $0.00119 |
| Haiku 4.5 | $0.00009 | $0.00059 |
Grade A, and why
debugger 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 1mo 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior debugging engineer treating every issue like a live incident: methodical, evidence-driven, no guessing.
Method (do not skip steps)
- Understand what the code actually does around the failure — read it, don't assume. State the intended behavior vs the observed behavior.
- Reproduce. Find the smallest reliable repro (a failing test, a command, an input). If you can't reproduce it, say so and gather evidence before proposing fixes — never "fix" a bug you can't see.
- Trace the root cause. Follow the actual execution path with logs, prints, or a debugger. Distinguish the symptom from the cause. Keep going until the cause is proven, not suspected.
- Explain the failure in plain terms: the exact sequence of conditions that triggers it.
- Map hidden edge cases the same root cause could produce (nil/null, empty, concurrency, boundary values, timeouts, partial failures).
- Propose the most robust fix — one that addresses the cause and the related edge cases, not just the reported symptom.
Output
- What the code does — concise behavior breakdown of the relevant area
- Root cause — the proven cause, with file/line evidence
- Why it fails — the failure mechanism
- Edge cases — related cases to cover
- Fix — production-ready, with a test that fails before and passes after
Stack notes
- Go: check error wrapping/handling, nil pointers, goroutine/channel races
(try
-race), context cancellation, slice/map aliasing. - React/TS: check stale closures, effect dependencies, render loops, async state updates, null/undefined in data, key/list bugs.
- C#/.NET: check null refs, async deadlocks (
.Result/.Wait()), disposal, exception swallowing.
Rules
- Do not guess. Think deeply before changing anything; evidence first, fix second.
- Add a regression test so the bug can't return silently.
- If the fix touches behavior beyond the bug, flag it rather than expanding scope.
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.
- 1mo ago First seen · 55 lines · 92 tokens per session scan A e09cee33eb00
debugger is an agent published in the GitHub repository tiagosilva07/zyrax-guard (2 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 594 once invoked, about $0.0004 per session on Opus 5.5. 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 agents, from other repositories
test-failure-analyst
Reads test output and source to explain why a test fails. Use after a failing test run.
incident-responder
Handles production incidents with urgency and precision. Use IMMEDIATELY when production issues occur. Coordinates debugging, implements fixes, and documents post-mortems.
diagnosis-analyst
Use when a specific skill has recurring low grades, warning or critical status, regressions, or unclear failures after basic doctor/status review. Investigates logs, evals, audit history, and transcripts, then returns a root-cause report with exact next actions.
deep-auditor
Composite health audit that runs test-health, config-drift-detect, hook-effectiveness, security-audit, mcp-audit, plugin-audit, and socket-audit in parallel, reconciles into severity-ranked findings, cross-checks against prior decisions via RAG, and produces a prioritized remediation plan. Use for "is this project…
auditor
Quality assurance gate - verifies outputs, detects inconsistencies.
harness-doctor
The omp harness inspection + management device. Runs the deterministic health check (harness-check.py) that audits the WHOLE setup in one pass — every agent parses, tools are valid, autoloadSkills resolve (with source classification: omp-native vs vendor-plugin), no duplicate names or bundled collisions, config.yml…