diagnosing-bugs

diagnosing-bugs is a skill for Claude Code, Codex from MoonTzai/folderbridge-mcp. It costs 25 tokens per session (248 once invoked), scanned A, original, Apache-2.0.

A bug-diagnosis process built around reproducing the user-visible failure, reducing it to a small case, and testing ranked explanations. A regression test is a test that prevents the same bug from returning.

In plain words
What is it for?
Investigating difficult bugs, creating minimal reproductions, choosing diagnostic checks, applying the smallest justified fix, and verifying it with focused and full test suites.
Why use it?
It replaces guesswork with a repeatable failing signal and targeted experiments. This helps separate the actual cause from nearby symptoms or misleading code clues.

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/moontzai/folderbridge-mcp/diagnosing-bugs
Any agent
npx skills add MoonTzai/folderbridge-mcp --skill diagnosing-bugs
Clone the repo
git clone --depth 1 https://github.com/MoonTzai/folderbridge-mcp

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 diagnosing-bugs

README.md
[![agentmods](https://agentmods.dev/badge/skills/moontzai/folderbridge-mcp/diagnosing-bugs.svg)](https://agentmods.dev/skills/moontzai/folderbridge-mcp/diagnosing-bugs)
Your own site
<a href="https://agentmods.dev/skills/moontzai/folderbridge-mcp/diagnosing-bugs"><img src="https://agentmods.dev/badge/skills/moontzai/folderbridge-mcp/diagnosing-bugs.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 248 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 $0.00025 $0.00248
Opus 5 $0.00013 $0.00124
Sonnet 5 $0.00005 $0.00050
Haiku 4.5 $0.00003 $0.00025

Measured 3d ago against content hash 851c215ef6ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diagnosing-bugs 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 3d 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.

skill_packs/matt-pocock-engineering/skills/diagnosing-bugs/SKILL.md · 15 lines

What it actually says

Diagnosing Bugs — FolderBridge Adaptation

For a hard bug, the first deliverable is a tight feedback loop that goes red on the user's actual symptom. Prefer a deterministic failing unit/integration/e2e test; otherwise use a minimal CLI harness, replay, differential check, or repeated stress loop. Do not build a theory from code reading before you can reproduce the failure.

Minimize the repro until unrelated variables are removed. Then generate several ranked, falsifiable hypotheses. Each hypothesis must predict what one targeted probe or controlled change would do. Instrument only at boundaries that distinguish those hypotheses; change one variable at a time.

Fix the smallest cause that explains the red signal, not nearby symptoms. Run the original repro first, then the relevant local tests, then the full regression suite. Keep a regression test that would have failed before the fix.

If the bug cannot be locked down because there is no stable test seam, treat that as an architecture finding and hand the seam problem to codebase-design / improve-codebase-architecture rather than hiding it with more logging or duplicated checks.

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. 3d ago First seen · 15 lines · 25 tokens per session scan A 851c215ef6ae

Subscribe to this mod's changes

diagnosing-bugs is a skill published in the GitHub repository MoonTzai/folderbridge-mcp (0 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 248 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.

Related

Other skills, from other repositories

erga-mcp

Use immediately when a user shares a job-posting URL—including a bare link or chat preview—and when organizing recruiting records, evaluating career evidence, or proposing a truthful résumé update through Erga MCP.

Adr1an04/erga-mcp · 44 tokens

mem0-dream

Consolidates stored memories by merging duplicates, resolving contradictions, and pruning stale entries. Use when memory count is high, search results feel noisy or repetitive, or periodic cleanup is needed to maintain memory quality.

mem0ai/mem0 · 46 tokens

mem0-vercel-ai-sdk

Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…

mem0ai/mem0 · 146 tokens

mem0-tour

Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.

mem0ai/mem0 · 47 tokens

onboard

Sets up mem0 for a new project including API key configuration, MCP authentication, project file import, and coding categories. Use on first run in a new project, when API key needs updating, or to re-run initial setup after configuration changes.

mem0ai/mem0 · 52 tokens

mem0-cli

Mem0 CLI -- the command-line interface for mem0 memory operations. TRIGGER when: user mentions "mem0 cli", "mem0 command line", "@mem0/cli", "mem0-cli", "pip install mem0-cli", "npm install -g @mem0/cli", or is running mem0 commands in a terminal/shell (mem0 add, mem0 search, mem0 list, mem0 get, mem0 init, mem0…

mem0ai/mem0 · 177 tokens