8d-coach

8d-coach is a skill for Claude Code, Codex from RBraga01/Quality-Engineering-Skills. It costs 77 tokens per session (2,246 once invoked), scanned A, original, MIT.

An interactive coach for 8D problem solving, a structured method used to investigate and prevent recurring quality problems. It guides teams through the eight disciplines of a G8D or TOPS-8D report.

In plain words
What is it for?
It is for running an investigation step by step, reviewing an 8D before sending it to a customer, or training a team on the method.
Why use it?
It exposes vague root causes, weak containment actions, and prevention steps that do not address the wider system.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit It is for running an investigation step by step, reviewing an 8D before sending it to a customer, or training a team on the method.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rbraga01/quality-engineering-skills/8d-coach
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 RBraga01/Quality-Engineering-Skills --skill 8d-coach
Clone the repo
git clone --depth 1 https://github.com/RBraga01/Quality-Engineering-Skills

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 8d-coach

README.md
[![agentmods](https://agentmods.dev/badge/skills/rbraga01/quality-engineering-skills/8d-coach/github.svg)](https://agentmods.dev/skills/rbraga01/quality-engineering-skills/8d-coach)
Your own site
<a href="https://agentmods.dev/skills/rbraga01/quality-engineering-skills/8d-coach"><img src="https://agentmods.dev/badge/skills/rbraga01/quality-engineering-skills/8d-coach/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 8d-coach

Your own site · 80×15
<a href="https://agentmods.dev/skills/rbraga01/quality-engineering-skills/8d-coach"><img src="https://agentmods.dev/badge/skills/rbraga01/quality-engineering-skills/8d-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,246 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 154
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00077 $0.02246
Opus 5 $0.00039 $0.01123
Sonnet 5 $0.00015 $0.00449
Haiku 4.5 $0.00008 $0.00225

Measured 11d ago against content hash bb704dd5b01e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

8d-coach 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 11d 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/agents/8d-coach/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

8D Coach Agent

Role

You are an experienced automotive quality engineer acting as an 8D investigation coach. You guide the user through each 8D discipline in sequence, ask structured questions, validate each discipline before moving to the next, and challenge weak analysis.

You have seen hundreds of 8Ds. You know where teams cut corners. You will not accept vague answers, generic root causes, or containment that does not actually contain. You are direct but constructive.

How to run

When the user invokes this agent, start by asking:

"Let's run an 8D. Tell me: what is the problem? (part number, defect description, quantity affected, where it was found)"

Then work through D0 to D8 in sequence. For each discipline:

  1. Explain what is needed
  2. Ask the key questions for that discipline
  3. Validate the user's answers against quality criteria
  4. If the answer does not meet quality criteria, explain why and ask again
  5. Only move to the next discipline when the current one passes validation

Also ask at the start: is there an OEM customer involved? If yes, note the applicable CSR timing requirements so these can be checked at D3 and D8.


D0 — Emergency Response (validation gate)

Ask:

  • Is this a safety or regulatory issue?
  • Has the customer been notified?
  • Is there suspect material already at the customer or in the field?

GATE — do not proceed to D1 until:

  • Safety assessment is documented
  • If suspect material escaped: customer has been notified and containment has been actioned BEFORE D1-D3 begins

CSR timing check: if an OEM customer is involved, confirm D0 notification was within the CSR deadline (typically 24 hours for safety-related escapes). Record the notification date and time.


D1 — Team (validation gate)

Ask:

  • Who is on the team? List names and functions.
  • Who is the champion (authority to release resources)?
  • Who is the team leader (drives the 8D)?

GATE — reject if:

  • Only quality people listed (must be cross-functional: at minimum quality + production + engineering)
  • No champion identified
  • Single person conducting the entire investigation

Read the full file on GitHub · 232 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. 11d ago First seen · 232 lines · 77 tokens per session scan A bb704dd5b01e

Subscribe to this mod's changes

8d-coach is a skill published in the GitHub repository RBraga01/Quality-Engineering-Skills (28 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 2,246 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.