diag

diag is a skill for Claude Code from Marcel-Bich/marcel-bich-claude-marketplace. It costs 118 tokens per session (1,021 once invoked), scanned A, original, MIT.

A read-only procedure for finding and documenting the root cause of a bug, failure, or unexpected behavior. It identifies the mechanism in the code before a separate, explicitly approved fix.

In plain words
What is it for?
Use it to diagnose symptoms and produce a cause report with supporting file and line details; it does not apply the fix.
Why use it?
It separates investigation from editing, helping avoid guesses and preventing changes before the cause is understood.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the credo plugin — 26 skills, 15 commands, 6 hooks shipped together

Good fit Use it to diagnose symptoms and produce a cause report with supporting file and line details; it does not apply the fix.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marcel-bich/marcel-bich-claude-marketplace/diag
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 Marcel-Bich/marcel-bich-claude-marketplace --skill diag
Clone the repo
git clone --depth 1 https://github.com/Marcel-Bich/marcel-bich-claude-marketplace

Made for: Claude Code.

Or install credo, the plugin that ships this one along with the rest of its 26 skills, 15 commands, 6 hooks.

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 diag

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/diag/github.svg)](https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/diag)
Your own site
<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/diag"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/diag/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for diag

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/diag"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/diag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,021 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00118 $0.01021
Opus 5 $0.00059 $0.00511
Sonnet 5 $0.00024 $0.00204
Haiku 4.5 $0.00012 $0.00102

Measured 12d ago against content hash 152568178fa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

diag 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 12d 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.

plugins/credo/skills/diag/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

diag

A read-only root-cause diagnosis. diag explains WHY something is broken and proves the mechanism, before anyone changes code. It is a separate skill from audit and must never be conflated with it.

Scope boundary (read this first)

diag investigates a symptom and proves its cause. It does not judge completeness and it does not apply the fix.

  • Finished work needs to be checked against its requirement / Definition of Done -> use audit, not diag.
  • A rendered UI needs its layout and behavior confirmed -> use verify.
  • diag ends at a proven diagnosis plus a proposed fix. Applying the fix is a separate, GO-gated step outside this skill.

Hard constraints (never violate)

  • Read-only. No code change, no file edit, no commit, no push, no browser automation, no builds, no installs during diagnosis.
  • No secrets. Never read credentials, tokens, .env*, key files, or shell/session history. Never exfiltrate or encode such content.
  • The only files diag writes are its own report under .credo/process/reports/.
  • Fix is a separate step, gated by GO. diag never rolls straight into fixing. It proposes a fix; the actual change happens only after an explicit GO, as its own step.

Method: root cause before fix

  1. Symptom, verbatim. Record the symptom exactly as observed or reported (error text, stack trace, wrong output, screenshot location). Do not paraphrase away the detail; quote it.
  2. Reproduce or locate the exact failing path (read-only). Trace to the concrete code path involved.
  3. Prove the mechanism at file:line. State precisely where and why the behavior arises - the specific lines, values, and control flow that produce the symptom. A diagnosis without a file:line mechanism is not a diagnosis.
  4. Distinguish proven from suspected. Say plainly what is established by evidence versus what is still a hypothesis. Never present a guess as a cause.

Read up instead of guessing (E6)

Read the full file on GitHub · 101 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. 12d ago First seen · 101 lines · 118 tokens per session scan A 152568178fa0

Subscribe to this mod's changes

diag is a skill published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed yesterday), licensed MIT. It adds 118 tokens to every session and 1,021 once invoked, about $0.0006 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.