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.
npx skills add RBraga01/Quality-Engineering-Skills --skill pfmea-processgit clone --depth 1 https://github.com/RBraga01/Quality-Engineering-SkillsWrote 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.
[](https://agentmods.dev/skills/rbraga01/quality-engineering-skills/pfmea-process)<a href="https://agentmods.dev/skills/rbraga01/quality-engineering-skills/pfmea-process"><img src="https://agentmods.dev/badge/skills/rbraga01/quality-engineering-skills/pfmea-process/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.
<a href="https://agentmods.dev/skills/rbraga01/quality-engineering-skills/pfmea-process"><img src="https://agentmods.dev/badge/skills/rbraga01/quality-engineering-skills/pfmea-process.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Anti-Refusal · line 146 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00086 | $0.02796 |
| Opus 5 | $0.00043 | $0.01398 |
| Sonnet 5 | $0.00017 | $0.00559 |
| Haiku 4.5 | $0.00009 | $0.00280 |
Grade A, and why
pfmea-process 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Process FMEA (PFMEA) — AIAG-VDA 2019
Goal
Identify and prioritise process risk before production — using the AIAG-VDA 2019 7-step approach — so that high-priority failure modes are eliminated or controlled before they reach the customer, and the result feeds directly into the Control Plan and Work Instructions.
Required Execution Checklist
- Scope defined: process step boundaries, model year, team assembled with cross-functional representation
- Process Flow Diagram (PFD) available and used as Step 2 input
- All process steps in the PFD have a corresponding entry in Structure Analysis (Step 2)
- Every process step has at least one Function defined in Step 3
- Failure chain complete for each function: Effect → Mode → Cause (in this direction — not reversed)
- All Failure Causes are evidence-based — no unverified assumptions used as final causes
- S/O/D ratings agreed by the cross-functional team and documented
- All Special Characteristics have S=9 or S=10
- Every H-AP item has a named owner, target date, and is tracked to closure
- PFMEA detection controls match the Control Plan; prevention controls match Work Instructions
When to use
- New process development (pre-production)
- Existing process change or transfer
- After a quality escape (update to reflect failure mode)
- Periodic review (IATF requires annual review or at change)
- Customer-specific requirement (Ford, GM, Stellantis, BMW, VW all require PFMEA)
Prerequisites
- Process flow diagram (PFD) — required for Step 2
- Product drawings with special characteristics identified
- DFMEA (if applicable) for effect severity reference
- Team: process engineer, quality engineer, production supervisor, maintenance
The 7-Step AIAG-VDA 2019 Approach
Step 1 — Planning and Preparation
Define the scope:
- FMEA header: part number, part name, model year, process step scope, revision, date, team
- Analysis boundary: which process steps are in scope (start point and end point)
- Timeline: new PFMEA or revision of existing?
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 278 lines · 86 tokens per session scan A 09099726e052
pfmea-process is a skill published in the GitHub repository RBraga01/Quality-Engineering-Skills (28 stars, last pushed 4d ago), licensed MIT. It adds 86 tokens to every session and 2,796 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.
Other skills, from other repositories
aqe-ruflo
Add optional Ruflo development-time orchestration to an Agentic QE workflow. Use when a task benefits from coordinated swarms, persistent cross-session memory, routing, or Ruflo hooks. Do not use for a one-shot edit, and never add Ruflo to shipped AQE runtime dependencies.
aqe-plan-work
Build dependency-aware execution plans for complex Agentic QE, Ruflo, integration, migration, or multi-stream engineering programs. Use when Codex must turn research or requirements into phased work, select a small AQE fleet, map critical paths and parallel streams, define acceptance gates, or sequence risky changes.…
aqe-research
Conduct evidence-first technical research for Agentic QE, Ruflo, related ruvnet projects, or external tools. Use when Codex must investigate a repository, compare current upstream changes, trace dependencies and history, distinguish verified facts from inference, or synthesize findings into actionable engineering…
aqe-plan-quality
Create risk-based quality and test plans for Agentic QE changes. Use when scoping a feature, translating requirements into verification work, selecting QE specialties, assessing testability, or deciding which .claude/agents/v3/qe-.md capabilities should inform a task. Do not use merely to execute an already-defined…
aqe-review-quality
Review Agentic QE changes and issue an evidence-backed quality verdict. Use for code review, regression-risk assessment, release readiness, quality-gate evaluation, security/performance/testability review, or checking whether a change has sufficient verification. Do not use when the user primarily asks to implement a…
aqe-test-change
Design, implement, and run durable tests for Agentic QE code changes. Use when adding tests, reproducing a defect, filling a coverage gap, selecting affected Vitest suites, checking CLI/MCP parity, or verifying a fix in this repository. Do not use for a read-only quality review with no requested edits.