Debugger

A systematic debugging workflow that investigates a software problem, tests possible causes, and produces a minimal fix strategy.

In plain words
What is it for?
Use it to investigate errors, unexpected behavior, production-only failures, failing tests, or performance regressions.
Why use it?
It helps separate the actual root cause from symptoms when a bug or failing test is not immediately clear.

Skill for Claude CodeCodex

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 skills/razaib-khan/forgeweave/debugger
Any agent
npx skills add Razaib-khan/ForgeWeave --skill debugger
Clone the repo
git clone --depth 1 https://github.com/Razaib-khan/ForgeWeave

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 656 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 $0.00020 $0.00656
Opus 5 $0.00010 $0.00328
Sonnet 5 $0.00004 $0.00131
Haiku 4.5 $0.00002 $0.00066

Measured 2d ago against content hash d7ba65d606f7, 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/hypothesis_tracker.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/forgeweave/templates/claude/.claude/skills/debugger/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugger

Purpose

Apply systematic debugging methodology to identify root causes of software issues. Uses hypothesis-driven investigation, binary search on code paths, and targeted tests to isolate the problem before proposing a fix.

When to Use

  • The user reports a bug, error, or unexpected behavior
  • A test is failing and the cause is not obvious
  • A feature works locally but fails in production
  • Performance regression needs investigation

When Not to Use

  • The error message is self-explanatory — fix it directly
  • The fix is already known and just needs implementation
  • The task is refactoring — use refactor-engine

Inputs

Input Type Required Description
symptom string Yes The observed error or unexpected behavior
reproduction_steps string No Steps to reproduce the issue
environment string No Environment details (OS, versions, deployment)
logs_or_stacktrace string No Error output, logs, or stack trace

Expected Outputs

Output Description
Root cause Identified source of the issue
Fix strategy Minimal change to fix the issue
Verification steps How to confirm the fix works
Prevention How to avoid similar issues

Exact Workflow Steps

  1. Understand the symptom and reproduction steps
  2. Formulate 2-3 hypotheses for root cause
  3. For each hypothesis, design a diagnostic test
  4. Narrow down by eliminating hypotheses
  5. Isolate the exact root cause
  6. Design minimal fix that doesn't break other functionality
  7. Verify fix resolves the symptom
  8. Run existing tests to confirm no regressions

Required Checks

  • Root cause is identified before any fix is proposed
  • Fix is minimal (no scope creep)
  • Existing tests pass after fix
  • Prevention strategy is documented

Failure Modes

Failure Condition Response
Cannot reproduce the issue Ask for more detailed reproduction steps
All hypotheses eliminated Broaden search to adjacent systems or dependencies
Fix breaks other functionality Revert and explore alternative fix strategy

Read the full file on GitHub · 94 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 94 lines · 20 tokens per session scan A d7ba65d606f7

Subscribe to this mod's changes

Debugger is a skill published in the GitHub repository Razaib-khan/ForgeWeave (1 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 656 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.