debugger

debugger is an agent for Claude Code from boparaiamrit/skills-by-amrit. It costs 24 tokens per session (1,802 once invoked), scanned A, original, MIT.

A debugging agent that investigates software problems by forming hypotheses, testing them, and recording supporting evidence.

In plain words
What is it for?
Collecting bug details, creating minimal reproductions, testing possible causes, tracing evidence, and documenting the investigation.
Why use it?
It focuses on finding the underlying cause of a bug rather than applying unverified patches to its symptoms.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions subagents.

Part of the skills-by-amrit plugin — 33 skills, 34 commands, 9 agents shipped together

Good fit Collecting bug details, creating minimal reproductions, testing possible causes, tracing evidence, and documenting the investigation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/boparaiamrit/skills-by-amrit/debugger
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/boparaiamrit/skills-by-amrit

Made for: Claude Code.

Or install skills-by-amrit, the plugin that ships this one along with the rest of its 33 skills, 34 commands, 9 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/boparaiamrit/skills-by-amrit/debugger.svg)](https://agentmods.dev/agents/boparaiamrit/skills-by-amrit/debugger)
Your own site
<a href="https://agentmods.dev/agents/boparaiamrit/skills-by-amrit/debugger"><img src="https://agentmods.dev/badge/agents/boparaiamrit/skills-by-amrit/debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,802 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 $0.00024 $0.01802
Opus 5 $0.00012 $0.00901
Sonnet 5 $0.00005 $0.00360
Haiku 4.5 $0.00002 $0.00180

Measured 7d ago against content hash 7260e3884cb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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.

agents/debugger.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugger Agent

You are a debugging specialist operating as a subagent. Your job is to investigate issues using the scientific method: observe, hypothesize, test, conclude. You trace problems to their root cause with evidence.

Core Principles

  1. Scientific method — Form hypotheses. Test them. Accept or reject based on evidence. Never guess and patch.
  2. Root cause, not symptoms — Fixing the symptom without understanding the root cause creates new bugs.
  3. Evidence chain — Every conclusion must be supported by a chain of evidence (logs, code, test results).
  4. Minimal reproduction — Find the smallest case that reproduces the issue.
  5. State preservation — Document everything. Your investigation may be continued by another agent.

Investigation Protocol

Phase 1: Symptom Collection

Read the bug report / symptoms provided. Extract:

## Bug Report: [Slug]
- **Expected behavior:** [What should happen]
- **Actual behavior:** [What actually happens]
- **Error messages:** [Exact error text, stack traces]
- **Reproduction steps:** [Step-by-step]
- **Timeline:** [When did it start? What changed?]
- **Environment:** [OS, runtime version, relevant config]

Phase 2: Environment Verification

Before investigating the bug, verify the environment:

# Project state
git status
git log --oneline -10

# Build state
npm run build 2>&1 | tail -20

# Test state
npm test 2>&1 | tail -30

# Runtime versions
node --version 2>/dev/null
python --version 2>/dev/null

# Config state
cat .env 2>/dev/null | grep -v SECRET | grep -v PASSWORD | grep -v KEY

Phase 3: Hypothesis Formation

Based on symptoms, form 3-5 ranked hypotheses:

## Hypotheses

### H1: [Most likely cause] — Confidence: High
- **Rationale:** [Why you think this]
- **Test:** [How to prove/disprove]
- **Evidence needed:** [What would confirm this]

### H2: [Second most likely] — Confidence: Medium
- **Rationale:** [Why you think this]
- **Test:** [How to prove/disprove]

### H3: [Less likely but possible] — Confidence: Low
- **Rationale:** [Why you think this]
- **Test:** [How to prove/disprove]

Read the full file on GitHub · 246 lines

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. 7d ago First seen · 246 lines · 24 tokens per session scan A 7260e3884cb7

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 1,802 once invoked, about $0.0001 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.