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 ppap-checkergit 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/ppap-checker)<a href="https://agentmods.dev/skills/rbraga01/quality-engineering-skills/ppap-checker"><img src="https://agentmods.dev/badge/skills/rbraga01/quality-engineering-skills/ppap-checker/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/ppap-checker"><img src="https://agentmods.dev/badge/skills/rbraga01/quality-engineering-skills/ppap-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.01422 |
| Opus 5.5 | $0.00031 | $0.00569 |
| Sonnet 5.5 | $0.00015 | $0.00284 |
| Haiku 4.5 | $0.00008 | $0.00142 |
Grade A, and why
ppap-checker 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 2mo 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPAP Checker Agent
When to use
Use this agent when:
- Preparing a PPAP package and want to verify nothing is missing before submission
- Reviewing a supplier's incoming PPAP and need a systematic gap assessment
- Confirming which elements are required for a specific PPAP level
- Generating a PPAP gap report for a customer or management review
Prerequisites
None. The agent will ask for all required information.
Workflow
The agent runs interactively in two modes:
MODE A: Submission preparation (build a PPAP)
The agent guides the user through each of the 18 PPAP elements in sequence, asking:
- Is this element complete? (Yes / No / Partial / N/A)
- If Yes: what document is this recorded in? (for evidence traceability)
- If No or Partial: what is missing?
At the end, the agent produces:
- Element-by-element status table
- Gap list with specific missing items
- Readiness verdict: Ready to submit / Not ready — n items outstanding
MODE B: Incoming PPAP review (audit a supplier's PPAP)
The agent asks the user to describe what the supplier has submitted for each element, then evaluates completeness and flags deficiencies.
Agent behaviour
Opening: Ask the user which mode they need (preparation vs. review), which PPAP Level (1–5), and which OEM customer is receiving the PPAP (to apply OEM-specific validation rules).
Production trial run check: Before reviewing individual elements, ask: "How many consecutive parts were produced in the production trial run?" If fewer than 300 (without written customer authorisation), flag immediately — the PPAP samples and capability data come from this run and the submission cannot be recommended until the run meets the minimum or a customer waiver is on file.
Level awareness: Skip elements that are not required for the stated level, and note which elements are optional vs. mandatory.
Validation gates per element:
| Element | Key validation question |
|---|---|
| 1 Design Records | Is the drawing at the correct, released revision? |
| 2 Engineering Change Documents | Is there an approved change document if a design change is involved? |
| 3 Customer Engineering Approval | Is written customer engineering sign-off obtained? |
| 4 DFMEA | Are all H-AP items actioned? Is it at the correct revision? |
| 5 Process Flow | Does it cover all operations from incoming material to shipment? |
| 6 PFMEA | Are all H-AP items actioned? Is it aligned with the Process Flow? |
| 7 Control Plan | Does it cover all special characteristics? Is it linked to the PFMEA? |
| 8 MSA | Is %GRR < 30% for all measurement systems on SC characteristics? Is ndc ≥ 5? |
| 9 Dimensional Results | Are ALL ballooned characteristics 100% conforming? Parts identified by cavity? |
| 10 Material/Performance Tests | Are all tests passed? Are lab reports from accredited labs? |
| 11 Initial Process Studies | Is Cpk ≥ 1.67 on all special characteristics? If Cpk 1.33–1.67: flag as conditional — customer monitoring required. If Cpk 1.00–1.33: block — 100% inspection AND customer-approved deviation required. If Cpk < 1.00: block — cannot submit. |
| 12 Qualified Lab Documentation | Are test labs accredited (ISO 17025 or equivalent)? |
| 13 AAR | Required only for appearance parts — is customer sign-off obtained? |
| 14 Sample Parts | Are parts from the production run (not prototype)? Labelled correctly? |
| 15 Master Sample | Is a signed master sample retained at the supplier? |
| 16 Checking Aids | Are all gauges calibrated? MSA complete for variable gauges? |
| 17 Customer-Specific Requirements | OEM-specific CSR items — confirmed with customer? |
| 18 PSW | Is it the correct form for this OEM? Signed by Quality Manager? |
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.
- 2mo ago First seen · 121 lines · 77 tokens per session scan A b3e7ce4adeda
ppap-checker is a skill published in the GitHub repository RBraga01/Quality-Engineering-Skills (43 stars, last pushed 7d ago), licensed MIT. It adds 77 tokens to every session and 1,422 once invoked, about $0.0003 per session on Opus 5.5. 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.
ppap-checker compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ppap-checkerRBraga01/Quality-Engineering-Skills | Skill | 43 | 7d ago | MIT | A | 77 | Claude Code, Codex |
| compliance-testingproffesor-for-testing/agentic-qe | Skill | 525 | yesterday | MIT | A | 43 | Claude Code |
| agile-v-gxp-qualificationAgile-V/agile_v_skills | Skill | 54 | 1mo ago | CC-BY-SA-4.0 | A | 61 | Claude Code |
| compliance-auditorAgile-V/agile_v_skills | Skill | 54 | 1mo ago | CC-BY-SA-4.0 | A | 58 | Claude Code |
| agile-v-complianceAgile-V/agile_v_skills | Skill | 54 | 1mo ago | CC-BY-SA-4.0 | A | 44 | Claude Code |
| documentation-agentAgile-V/agile_v_skills | Skill | 54 | 1mo ago | CC-BY-SA-4.0 | A | 76 | Claude Code |
| risk-management-specialistchenxihuang1028-a11y/risk-management-specialist | Skill | 6 | 3mo ago | MIT | A | 82 | Claude Code, Codex |