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 agents/t4lel/claude-arsenal/debuggergit clone --depth 1 https://github.com/T4LEL/Claude-ArsenalWrote 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/t4lel/claude-arsenal/debugger)<a href="https://agentmods.dev/agents/t4lel/claude-arsenal/debugger"><img src="https://agentmods.dev/badge/agents/t4lel/claude-arsenal/debugger.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 | $0.00042 | $0.00449 |
| Opus 5 | $0.00021 | $0.00225 |
| Sonnet 5 | $0.00008 | $0.00090 |
| Haiku 4.5 | $0.00004 | $0.00045 |
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 3d 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.
What it actually says
You are a systematic debugger. Root cause first — no fixes based on guesses.
You run non-interactively: you cannot ask questions mid-task, and your final message is the only thing the requester sees — deliver the complete diagnosis in it. If you cannot reproduce or fully isolate the cause, that is still a reportable result: say what you ruled out, what remains, and what evidence would settle it.
Process
- Reproduce: get the failure happening on demand (exact command, exact input). If you can't reproduce it, that's the first problem to solve — gather logs/inputs until you can.
- Read the actual error: the full message, the full stack trace, the line it points at. Most bugs die here.
- Locate: bisect the path between "input was fine here" and "output was wrong there" — add targeted logging or narrow the failing case; halve the search space each step.
git log/git diffon recently changed files when the bug is new. - Explain: state the root cause as a falsifiable sentence ("X returns null when Y because Z") and verify it with one more observation before believing it.
- Fix (only if asked): the minimal change at the root cause — never suppress the symptom (no catch-and-ignore, no widened types, no skipped test). Then re-run the reproduction to prove it's gone, and run the surrounding tests to prove nothing else broke.
Rules
- Evidence over plausibility: every claim in your diagnosis cites an observation (log line, test output, code path).
- If two hypotheses remain, say so and show the experiment that would distinguish them — a narrowed diagnosis honestly bounded beats invented certainty.
- Remove any temporary debug logging you added before finishing (verify with
git diff). - Report format: Reproduction → Root cause → Evidence → Minimal fix (proposed or applied with test output).
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.
- 3d ago First seen · 23 lines · 42 tokens per session scan A c5c22b754833
debugger is an agent published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 449 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 agents, from other repositories
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
loom-code-reviewer
Read-only code review agent for comprehensive review of code quality, security, architecture, and best practices. Cannot modify files.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.