debug

A command for diagnosing a Parallax problem using evidence from reproduction steps, project files, tests, logs, and verification. It can also verify a repair after the cause is identified.

In plain words
What is it for?
Use it to investigate a reproducible failure, trace its state and timing, apply a focused fix, add a regression check when practical, and report evidence and remaining risk.
Why use it?
It separates confirmed facts from guesses and focuses on root causes instead of hiding symptoms. It also scales verification to the likely impact of the change.

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/master0ffate/parallax-claudecode/debug
Any agent
npx skills add Master0fFate/parallax-claudecode --skill debug
Clone the repo
git clone --depth 1 https://github.com/Master0fFate/parallax-claudecode

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 215 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 $0.00018 $0.00215
Opus 5 $0.00009 $0.00108
Sonnet 5 $0.00004 $0.00043
Haiku 4.5 $0.00002 $0.00021

Measured yesterday against content hash 14e9a54213f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug 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.

skills/debug/SKILL.md · 19 lines

What it actually says

Debug

Pass the current Claude session ID to parallax_debug. Audit $ARGUMENTS with professional skepticism.

  1. Establish the expected behavior and reproduce the symptom with the narrowest reliable command.
  2. Separate direct evidence, strong inference, and unknowns. Trace state ownership, feedback, coupling, and timing before proposing a cause.
  3. Rank findings by material impact and likelihood. Cite paths, tests, logs, or command output; ignore cosmetic noise unless requested.
  4. Fix root causes rather than suppressing errors. Keep the patch surgical and add a regression check that fails before the fix when practical.
  5. Run targeted verification, then broader checks proportional to blast radius.

Report diagnosis, root cause, changed files, test evidence, limitations, and remaining risk. If evidence is insufficient, say so rather than assigning a confident verdict.

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 · 19 lines · 18 tokens per session scan A 14e9a54213f8

Subscribe to this mod's changes

debug is a skill published in the GitHub repository Master0fFate/parallax-claudecode (0 stars, last pushed 9d ago), licensed MIT. It adds 18 tokens to every session and 215 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.