cm-debugging

A process to follow when a program has a bug, a test fails, or its behavior is unexpected, before suggesting a fix.

In plain words
What is it for?
Use it to investigate defects, failing tests, and behavior that does not match expectations.
Why use it?
It encourages investigation of the actual cause instead of jumping straight to an unverified 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/tody-agent/codymaster/cm-debugging
Any agent
npx skills add tody-agent/codymaster --skill cm-debugging
Clone the repo
git clone --depth 1 https://github.com/tody-agent/codymaster

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 2,423 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.02423
Opus 5 $0.00010 $0.01211
Sonnet 5 $0.00004 $0.00485
Haiku 4.5 $0.00002 $0.00242

Measured 2d ago against content hash 1af687c4a84d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cm-debugging 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/cm-debugging/SKILL.md · 313 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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 · 313 lines · 20 tokens per session scan A 1af687c4a84d

Subscribe to this mod's changes

cm-debugging is a skill published in the GitHub repository tody-agent/codymaster (52 stars, last pushed 7d ago), with no licence file. It adds 20 tokens to every session and 2,423 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 2026-08-30.

Related

Other skills, from other repositories

eduorchestrate

Use /eduorchestrate to onboard a learner, create an adaptive job-role plan with a 30-day minimum, research trends, send daily plan emails, log progress, load the prebuilt skill progression card, summarize weeks, recommend the next skill, and review progress.

haroontrailblazer/EduOrchestrate · 60 tokens

eduorchestrate

Universal EduOrchestrate adapter for openclaw. Use /eduorchestrate for learner onboarding, adaptive plans with a 30-day minimum, trend research, daily email plans, progress logging, prebuilt skill progression cards, weekly summaries, and next-skill recommendations.

haroontrailblazer/EduOrchestrate · 60 tokens

scale-to-millions

Use this skill whenever the user is designing, reviewing, debugging, or answering interview questions about system/software architecture and scalability — e.g. "scale my app", "how do I handle more traffic", "design a URL shortener / news feed / chat system", "my API is slow under load", "should I shard my database"…

Rudra-narayan-muduli-001/Scale-to-Millions · 130 tokens

wiki_inbox

Put papers into a knowledge base from whatever the user has — an arXiv link, a journal page, a DOI, a citation, or a screenshot. Identifies each one, queues it, runs the deterministic ingest pipeline, and hands the batch back for approval.

Misaka16384/magi · 58 tokens

wiki_ingest

Ingest new academic papers, notes, or web articles into the raw/ folder of your active topic wiki.

Misaka16384/magi · 26 tokens

wiki_research

Spawn parallel academic subagents to perform multi-perspective research on a given query and compile a detailed synthesis report.

Misaka16384/magi · 26 tokens