conducty-debug

conducty-debug is a skill for Claude Code, Codex from robertbarclayy/conducty. It costs 66 tokens per session (1,709 once invoked), scanned A, original, MIT.

A failure-analysis guide for coding-agent prompts. It separates problems in the overall plan, the instructions given to the agent, and the code being changed.

In plain words
What is it for?
Use it to investigate failed prompts, checkpoint issues, unsuccessful fixes, or requests to find out why work failed.
Why use it?
It helps avoid fixing the wrong layer and wasting repeated attempts when a task fails verification.

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

Made for: Claude Code, 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 conducty-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/robertbarclayy/conducty/conducty-debug.svg)](https://agentmods.dev/skills/robertbarclayy/conducty/conducty-debug)
Your own site
<a href="https://agentmods.dev/skills/robertbarclayy/conducty/conducty-debug"><img src="https://agentmods.dev/badge/skills/robertbarclayy/conducty/conducty-debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,709 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 $0.00066 $0.01709
Opus 5 $0.00033 $0.00855
Sonnet 5 $0.00013 $0.00342
Haiku 4.5 $0.00007 $0.00171

Measured 5d ago against content hash 7daa15529e72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conducty-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 5d 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.

skills/conducty-debug/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conducty Debug — Leverage Point Analysis

When something fails, the first question is not "what's wrong with the code?" It's "where is the highest leverage point to fix this?" A failure might be a code bug, a prompt quality problem, a plan assumption error, or a systemic issue affecting multiple prompts. Fixing at the wrong level wastes retries.

The Leverage Hierarchy

Fix at the highest level that applies:

Plan assumptions  →  fixes the most, prevents future failures
  ↓
Prompt quality    →  fixes this prompt and similar future prompts
  ↓
Code bug          →  fixes this specific failure only

Plan-level fix: The design was wrong, the acceptance criteria were incorrect, or the context was insufficient. A code fix won't help because the code was implementing the wrong thing correctly. Signal: the tracer failed, or multiple prompts in the same group fail for related reasons.

Prompt-level fix: The prompt was vague, missing context, had no no-go zones, or specified the wrong approach. The code did what the prompt said, but the prompt said the wrong thing. Signal: spec review passes but verification fails, or the implementer was BLOCKED/NEEDS_CONTEXT.

Code-level fix: The prompt was clear and correct, but the implementation had a bug. This is the only case where a traditional "fix the code" approach is appropriate. Signal: the failure is in specific logic, not in misunderstanding.

The Four Phases

Phase 1: Classify the Failure

Before doing anything else, determine the leverage point:

  1. Read the failure output carefully. What exactly failed? Not "tests fail" but which test, which assertion, what value.

  2. Compare failure against the prompt. Did the implementer build what the prompt asked for? If yes, the problem is the prompt or the plan, not the code. If no, it might be a code bug.

  3. Check if this is systemic. Are other prompts in the same group failing? Do they share assumptions, context, or dependencies? If 2+ prompts fail in the same group, suspect a plan-level issue before investigating individual code bugs.

Read the full file on GitHub · 160 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. 5d ago First seen · 160 lines · 66 tokens per session scan A 7daa15529e72

Subscribe to this mod's changes

conducty-debug is a skill published in the GitHub repository robertbarclayy/conducty (176 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 1,709 once invoked, about $0.0003 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens