debugger

debugger is an agent for Claude Code from jeremylongshore/tons-of-skills-marketplace. It costs 46 tokens per session (432 once invoked), scanned A, original, MIT.

A debugging specialist that investigates the underlying cause of bugs, failed tests, and regressions, where a regression is a problem that returns after a change. It uses a step-by-step questioning method and tests competing explanations before proposing a patch.

In plain words
What is it for?
Reproducing failures, researching relevant library issues, testing hypotheses, applying a root-cause fix, and adding a test that catches the regression.
Why use it?
It reduces the risk of fixing only a visible symptom and requires evidence that the fix addresses the real cause.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the hyperflow plugin — 28 skills, 22 agents shipped together

Good fit Reproducing failures, researching relevant library issues, testing hypotheses, applying a root-cause fix, and adding a test that catches the regression.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jeremylongshore/tons-of-skills-marketplace/debugger
About the project

Tons of Skills is a model-agnostic marketplace that distributes reusable skills, plugins, agents, commands, hooks, and settings for coding-agent tools. It is intended for people who want to browse, install, and manage agent extensions, with Claude Code as its verified native harness. The catalogue entries are extensions provided by or associated with this marketplace.

jeremylongshore/tons-of-skills-marketplace · 2,717 stars · on GitHub · tonsofskills.com

Install

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.

Clone the repo
git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace

Made for: Claude Code.

Or install hyperflow, the plugin that ships this one along with the rest of its 28 skills, 22 agents.

Wrote 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.

agentmods badge for debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/debugger/github.svg)](https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/debugger)
Your own site
<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/debugger"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/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.

agentmods 80×15 button for debugger

Your own site · 80×15
<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/debugger"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 432 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00432
Opus 5 $0.00023 $0.00216
Sonnet 5 $0.00009 $0.00086
Haiku 4.5 $0.00005 $0.00043

Measured 13d ago against content hash e438d520cc30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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 13d 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.

plugins/ai-agency/hyperflow/agents/debugger.md · 29 lines

What it actually says

Family: Investigator · Binds personas: bugfix, test · Default role: investigator · Triggered by types: bugfix, test, performance (regression).

Mission: Find the cause, not a symptom — reproduce, gather evidence, form competing hypotheses, test them in parallel, and fix at the root with a regression test that fails on the old code.

Web-research-first: per ../skills/hyperflow/web-research.md. Scope: known issues / changelogs for the implicated library version, error-signature lookups. Gated flows only (trace is gated-in for non-trivial bugs).

Sub-agent fan-out: allowed — depth 1, ≤ 3 sub-workers, one per competing hypothesis, run in parallel; the debugger synthesizes their evidence into a verdict. Single-hypothesis bugs never fan out.

Strict checklist / output contract: apply the bugfix and test personas' verification plus:

  • A reproduction exists before any fix; the 5-Whys chain is written down, not skipped.
  • Each hypothesis has a concrete test that would confirm or kill it — no blind patching of symptoms.
  • The fix addresses the root the chain identified; a regression test fails on the old code and passes on the new.
  • No unrelated changes ride along with the fix.

Output format: findings block — root cause + evidence chain + fix location; Sources consulted: when research ran.

Composes with: dispatches searcher sub-workers for evidence; hands the fix surface to the matching domain reviewer. Defers to security-reviewer if the root cause is a security defect.

Changes

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.

  1. 13d ago First seen · 29 lines · 46 tokens per session scan A e438d520cc30

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,717 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 432 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.