safe-debug

safe-debug is a skill for Codex from lllllllama/RigorPilot-Skills. It costs 88 tokens per session (429 once invoked), scanned A, original, MIT.

A cautious debugging guide for deep-learning failures such as tracebacks, CUDA out-of-memory errors, checkpoint problems, shape mismatches, NaN loss, or failed training.

In plain words
What is it for?
Use it to narrow down the cause of a training or inference failure, document evidence, and suggest the smallest fix before modifying the repository.
Why use it?
It separates diagnosis from code changes and distinguishes a practical repair from a change to the research method.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to narrow down the cause of a training or inference…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lllllllama/rigorpilot-skills/safe-debug
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.

Any agent
npx skills add lllllllama/RigorPilot-Skills --skill safe-debug
Clone the repo
git clone --depth 1 https://github.com/lllllllama/RigorPilot-Skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for safe-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/lllllllama/rigorpilot-skills/safe-debug.svg)](https://agentmods.dev/skills/lllllllama/rigorpilot-skills/safe-debug)
Your own site
<a href="https://agentmods.dev/skills/lllllllama/rigorpilot-skills/safe-debug"><img src="https://agentmods.dev/badge/skills/lllllllama/rigorpilot-skills/safe-debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 429 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00088 $0.00429
Opus 5 $0.00044 $0.00215
Sonnet 5 $0.00018 $0.00086
Haiku 4.5 $0.00009 $0.00043

Measured today against content hash 2c3a51de17d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

safe-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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/safe_debug.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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/safe-debug/SKILL.md · 46 lines

What it actually says

safe-debug

Use this as the Rigor Debug / Rigor Audit skill. The installed slug remains safe-debug for compatibility.

Use the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md; this skill should guide conservative diagnosis without blocking the model from finding the local root cause.

When to apply

  • The user provides a traceback, terminal error, or concrete training or inference failure symptom.
  • The user wants diagnosis, root-cause narrowing, and minimal patch suggestions before code is changed.
  • The user wants a safe debug flow with explicit human approval before mutation.

When not to apply

  • When the user wants a broad repository walkthrough without an active failure.
  • When the task is speculative experimentation or code adaptation.
  • When the user is asking for a large refactor or readability rewrite.

Clear boundaries

  • Diagnose first.
  • Do not modify repository code by default.
  • If a patch is needed, propose the smallest fix and require explicit approval first.
  • Escalate savepoint or branch creation before medium-risk or high-risk changes.
  • A debug fix is not automatically a research contribution; if it changes experiment meaning or comparability, say so explicitly.

Output expectations

  • debug_outputs/DIAGNOSIS.md
  • debug_outputs/PATCH_PLAN.md
  • debug_outputs/status.json

Notes

Use references/debug-policy.md, ../ai-research-reproduction/references/research-rigor-principles.md, and the shared ../ai-research-reproduction/references/research-pitfall-checklist.md.

Files

What ships with it

3 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. today Changed 2c3a51de17d8
  2. 7d ago First seen · 46 lines · 88 tokens per session scan A f1337a643a8f

Subscribe to this mod's changes

safe-debug is a skill published in the GitHub repository lllllllama/RigorPilot-Skills (484 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 429 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

trace

Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode.

Yeachan-Heo/oh-my-claudecode · 18 tokens

smiles-validation

Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.

synthetic-sciences/openscience · 24 tokens

social-physics-filter

Unified boundary enforcement, interpersonal diagnostic, and relational audit engine. Absorbs 40 psychology + 2 social protocols and all relationship case studies.

winstonkoh87/Athena-Public · 34 tokens

cnsplots

Create, revise, and troubleshoot publication-ready scientific plots in Python with cnsplots, including distribution, regression, heatmap, genomics, survival, set, flow, and multi-panel figures. Use when a user asks for cnsplots code, Cell/Nature/Science-style visualization, precise pixel-sized figures, statistical…

faridrashidi/cnsplots · 79 tokens

relax-dev-debug

Develop and debug the Relax reinforcement learning project. Use this skill whenever modifying code in the relax/ directory, or running remote training jobs on a Ray cluster for validation. Also use it when the user mentions training, debugging training runs, submitting Ray jobs, or fixing training errors.

redai-infra/Relax · 60 tokens

thinking-scientific-method

When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.

tjboudreaux/cc-thinking-skills · 38 tokens