protocol-d-debugging

A step-by-step method for debugging software called Protocol D: read the error, isolate the cause, check documentation, form a hypothesis, and verify it.

In plain words
What is it for?
Use it when investigating crashes, bugs, failing tests, error messages, or code that is not working as expected.
Why use it?
It replaces random guessing with a repeatable way to narrow down what went wrong. It is intended for errors, broken behavior, failed code, and situations where you are stuck.

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/danielpodolsky/ownyourcode/debugging
Any agent
npx skills add DanielPodolsky/ownyourcode --skill debugging
Clone the repo
git clone --depth 1 https://github.com/DanielPodolsky/ownyourcode

Made for: Claude Code, Codex.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,319 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 $0.00075 $0.02319
Opus 5 $0.00037 $0.01159
Sonnet 5 $0.00015 $0.00464
Haiku 4.5 $0.00007 $0.00232

Measured 2d ago against content hash 3b1302395add, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

protocol-d-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.

.claude/skills/fundamentals/debugging/SKILL.md · 315 lines

How it starts

The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Protocol D: Systematic Debugging

"Debugging is not guessing. It's a systematic elimination of possibilities."

When to Apply

Activate this skill when:

  • Junior says "it's not working" or "I'm stuck"
  • Junior encounters an error they don't understand
  • Junior has been spinning on the same problem
  • Junior is frustrated and can't find the bug
  • Junior asks "why isn't this working?"

The Protocol D Framework

┌─────────────────────────────────────────────────────────────────┐
│                      PROTOCOL D                                  │
│              Systematic Debugging Flow                           │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  STEP 1: READ                                                    │
│  ────────────────────────────────────────────────                │
│  "Read the error message OUT LOUD. What is it actually saying?"  │
│                                                                  │
│  - Don't skim. Read every word.                                  │
│  - What file? What line? What type of error?                     │
│  - Is there a stack trace? Follow it.                            │
│                                                                  │
│                         ↓                                        │
│                                                                  │
│  STEP 2: ISOLATE                                                 │
│  ────────────────────────────────────────────────                │
│  "Where EXACTLY is the failure? Can you point to the line?"      │
│                                                                  │
│  - Frontend or Backend?                                          │
│  - Which function? Which line?                                   │
│  - Add console.log/print statements to narrow down               │
│  - Binary search: comment out half, does it still fail?          │
│                                                                  │
│                         ↓                                        │
│                                                                  │
│  STEP 3: DOCS                                                    │
│  ────────────────────────────────────────────────                │
│  "What does the official documentation say about this?"          │
│                                                                  │
│  - Google the EXACT error message                                │
│  - Check official docs for the function/API                      │
│  - Read the types/signatures carefully                           │
│  - Are you using it correctly?                                   │
│                                                                  │
│                         ↓                                        │
│                                                                  │
│  STEP 4: HYPOTHESIZE                                             │
│  ────────────────────────────────────────────────                │
│  "What do YOU think the problem is? Form a hypothesis."          │
│                                                                  │
│  - Based on the error and your investigation                     │
│  - What's your best guess?                                       │
│  - What would need to be true for your code to work?             │
│  - What assumption might be wrong?                               │
│                                                                  │
│                         ↓                                        │
│                                                                  │
│  STEP 5: VERIFY                                                  │
│  ────────────────────────────────────────────────                │
│  "Test your hypothesis. Did it work? Why or why not?"            │
│                                                                  │
│  - Make ONE change at a time                                     │
│  - Did it fix it? Great, explain WHY                             │
│  - Didn't fix it? What did you learn? New hypothesis.            │
│  - Loop until resolved                                           │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 315 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 · 315 lines · 75 tokens per session scan A 3b1302395add

Subscribe to this mod's changes

protocol-d-debugging is a skill published in the GitHub repository DanielPodolsky/ownyourcode (276 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 2,319 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

agent-release-swarm

Agent skill for release-swarm - invoke with $agent-release-swarm.

ruvnet/ruflo · 19 tokens

agent-code-analyzer

Agent skill for code-analyzer - invoke with $agent-code-analyzer.

ruvnet/ruflo · 19 tokens

agui-dotnet-streaming-chat

Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…

ag-ui-protocol/ag-ui · 223 tokens

agui-dotnet-sample-step

Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…

ag-ui-protocol/ag-ui · 168 tokens

agui-dotnet-protobuf

Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…

ag-ui-protocol/ag-ui · 162 tokens

github-pr-description

Generate and create pull request descriptions automatically using GitHub CLI. Use when the user asks to create a PR, generate a PR description, make a pull request, or submit changes for review. Analyzes git diff and commit history to create comprehensive, meaningful PR descriptions that explain what changed, why it…

tailcallhq/forgecode · 72 tokens