codexspec:debug

A systematic debugging workflow that traces a reported failure back to its root cause before fixing it.

In plain words
What is it for?
Use it to investigate software failures, identify the underlying problem, apply one targeted fix, and verify that the failure is resolved.
Why use it?
It prevents symptom-only patches, such as hiding an error without resolving why it happens. The workflow requires the cause to be established before a fix is proposed.

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/zts0hg/codexspec/codexspec-debug
Any agent
npx skills add Zts0hg/codexspec --skill codexspec-debug
Clone the repo
git clone --depth 1 https://github.com/Zts0hg/codexspec

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,083 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 $0.00017 $0.01083
Opus 5 $0.00009 $0.00541
Sonnet 5 $0.00003 $0.00217
Haiku 4.5 $0.00002 $0.00108

Measured 2d ago against content hash c3c7731905ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codexspec: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 2d 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/skills/codexspec-debug/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systematic Debugger

Language Preference

Read .codexspec/config.yml. Two independent language controls apply (each falls back to language.output, then English):

  • Interaction language (language.interaction): language for all conversation with the user — questions, explanations, status messages, and codexspec CLI terminal output.
  • Document language (language.document): language for generated artifact files (requirements/spec/plan/tasks).

Converse in the interaction language and author artifacts in the document language. Apply the project's translation standard to both: translate by meaning (not word-for-word), keep English for terms with no good native equivalent, and write as if originally in that language.

User Input

the text after the $codexspec:debug skill mention

Role and Iron Law

You debug a reported symptom to its root cause and apply exactly one verified fix.

Iron Law: NO FIX BEFORE ROOT CAUSE. You MUST NOT propose, apply, or even sketch a fix until Phase 1 has established what is actually wrong and why. Symptom patches — wrapping the error, silencing a failing assertion, retrying blindly — are failures, not fixes.

Red flags that mean STOP and return to Phase 1: "let me just try changing X", "add a try/except here", "it's probably the Y" — any edit attempted before the failure is reproduced and understood.

You leave no persistent artifact: no report file, no debug journal. Your output is the fix plus a concise root-cause explanation in the conversation. (Reusable, cross-feature lessons are captured separately by $codexspec:distill, never written here.)

Symptom Intake

Take the symptom from the text after the $codexspec:debug skill mention when provided — an error or stack trace, a failing-test id, a file:line, or a plain-language description — otherwise from error output already visible in this session.

When the symptom is too thin to act on, reproduce-or-ask before doing anything else:

  • First attempt to reproduce it yourself: run the failing test, exercise the path, read the log or stack trace.
  • If you still cannot reproduce it reliably, ask the user for exactly what is missing — reproduction steps, the precise input that triggers it, expected-vs-actual behavior, the verbatim error, and when it started.
  • Do NOT propose a fix for an unreproduced symptom.

Read the full file on GitHub · 80 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. 2d ago First seen · 80 lines · 17 tokens per session scan A c3c7731905ee

Subscribe to this mod's changes

codexspec:debug is a skill published in the GitHub repository Zts0hg/codexspec (5 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 1,083 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.

Related

Other skills, from other repositories

airflow-translations

Add or update translations for the Apache Airflow UI. Guides through setting up locales, scaffolding translation files, translating with locale-specific guidelines, and validating results. Use when working with i18n tasks in airflow-core/src/airflow/ui/public/i18n/locales/.

apache/airflow · 60 tokens

intlayer-angular

Integrates Intlayer internationalization with Angular applications. Use when the user asks to "setup Angular i18n", create a new translated component, use the "useIntlayer" composable, or configure providers.

aymericzip/intlayer · 47 tokens

intlayer-next-js

Integrates Intlayer internationalization with Next.js App Router and Pages Router. Use when the user asks to "setup Next.js i18n", use "useIntlayer" in Server Components, or handle client-side translations in Next.js.

aymericzip/intlayer · 53 tokens

intlayer-react

Integrates Intlayer internationalization with React component. Use when the user asks to "setup React i18n", create a new translated component, use the "useIntlayer" hook, or configure providers.

aymericzip/intlayer · 46 tokens

intlayer-cli

Manages Intlayer dictionaries and configuration via the Command Line Interface. Use when the user asks to "audit translations", "build dictionaries", "sync content", or run "intlayer" commands.

aymericzip/intlayer · 43 tokens

intlayer-preact

Integrates Intlayer internationalization with Preact applications. Use when the user asks to "setup Preact i18n", create a new translated component, use the "useIntlayer" hook in Preact, or configure providers.

aymericzip/intlayer · 52 tokens