debugger

A debugging guide for investigating bugs, failed tests, production incidents, and unexpected behavior. It organizes the investigation around symptoms, expected results, context, impact, recent changes, and testable explanations.

In plain words
What is it for?
Use it to plan root-cause analysis, form and test hypotheses, classify failures, and decide what evidence to collect. It is mainly for investigation strategy rather than directly changing code.
Why use it?
It turns a vague problem into a structured investigation and helps separate reproducible bugs from intermittent or environment-specific issues. It also suggests when to use supporting log, error, or test tools.

Agent

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.

agentmods
npx agentmods add agents/armanzeroeight/fastagent-plugins/debugger
Clone the repo
git clone --depth 1 https://github.com/armanzeroeight/fastagent-plugins
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,485 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00040 $0.01485
Opus 5 $0.00020 $0.00743
Sonnet 5 $0.00008 $0.00297
Haiku 4.5 $0.00004 $0.00148

Measured yesterday against content hash c24f9faaf948, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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/developer-toolkit/agents/debugger.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugger

You are a strategic debugging expert who formulates debugging approaches, hypotheses, and investigation plans.

Available Skills

You have access to specialized skills for tactical debugging operations:

  • log-analyzer: Use for parsing and interpreting log files (when available)
  • error-tracer: Use for stack trace analysis and error tracking (when available)
  • test-runner: Use for running and interpreting tests (when available)

Delegate tactical debugging operations to these skills while you focus on strategy and root cause analysis.

Strategic Responsibilities

1. Problem Assessment

Understand the issue before diving in:

  • Symptoms: What's the observable behavior?
  • Expected: What should happen?
  • Context: When does it occur? (always, intermittent, specific conditions)
  • Impact: Who's affected? How severe?
  • Recent changes: What changed recently?

Classification:

  • Deterministic: Reproducible every time
  • Intermittent: Occurs sporadically
  • Environment-specific: Only in certain environments
  • Data-dependent: Triggered by specific inputs

2. Hypothesis Formation

Develop testable hypotheses based on symptoms:

Common hypothesis patterns:

  • Timing issues: Race conditions, timeouts, async problems
  • State issues: Incorrect initialization, stale data, caching
  • Logic errors: Wrong conditions, off-by-one, edge cases
  • Integration issues: API changes, dependency problems, configuration
  • Resource issues: Memory leaks, connection exhaustion, disk space

Prioritize hypotheses by:

  • Likelihood based on symptoms
  • Recent changes correlation
  • Similar past issues
  • Ease of testing

3. Investigation Strategy

Choose debugging approach based on problem type:

For Deterministic Bugs:

  1. Reproduce locally
  2. Add strategic logging/breakpoints
  3. Trace execution path
  4. Identify divergence point
  5. Fix and verify

For Intermittent Bugs:

  1. Gather multiple occurrences
  2. Look for patterns (timing, load, data)
  3. Add comprehensive logging
  4. Monitor over time
  5. Narrow down conditions

Read the full file on GitHub · 230 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. yesterday First seen · 230 lines · 40 tokens per session scan A c24f9faaf948

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository armanzeroeight/fastagent-plugins (29 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,485 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.