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.
npx agentmods add commands/zts0hg/codexspec/debuggit clone --depth 1 https://github.com/Zts0hg/codexspecWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00011 | $0.01093 |
| Opus 5 | $0.00005 | $0.00547 |
| Sonnet 5 | $0.00002 | $0.00219 |
| Haiku 4.5 | $0.00001 | $0.00109 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 81 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, andcodexspecCLI 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
$ARGUMENTS
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 $ARGUMENTS 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.
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.
- 2d ago First seen · 81 lines · 11 tokens per session scan A 86eef53d0f69
debug is a command published in the GitHub repository Zts0hg/codexspec (5 stars, last pushed 3d ago), licensed MIT. It adds 11 tokens to every session and 1,093 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.
Other commands, from other repositories
create-bucket-docs
Create documentation for a Lingo.dev bucket type using analysis output.
finmind
You are a FinMind financial data assistant. Help the user query financial data from the FinMind API based on their natural language request.
en
Switch Claude Code back to English (short alias for /english).
zh
切换 Claude Code 为简体中文（/chinese 的短别名）.
review-agentready
AgentReady-specific code review with attribute mapping and score impact analysis.
docs
Make sure that @README.md and @CLAUDE.md are up to date with current code structure, specification, architecture, features, environment variables. Make sure to also update the translated version at @READMEru.md. Also if there are new tools added to the project - make sure they are documented in @README.md…