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 control-plan-buildergit 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/control-plan-builder)<a href="https://agentmods.dev/skills/rbraga01/quality-engineering-skills/control-plan-builder"><img src="https://agentmods.dev/badge/skills/rbraga01/quality-engineering-skills/control-plan-builder.svg" alt="Measured on agentmods" 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 | $0.00095 | $0.01581 |
| Opus 5 | $0.00048 | $0.00790 |
| Sonnet 5 | $0.00019 | $0.00316 |
| Haiku 4.5 | $0.00010 | $0.00158 |
Grade A, and why
control-plan-builder 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 7d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Control Plan Builder Agent
When to use
Use this agent when:
- Building a new Control Plan from scratch — the agent builds it row by row
- Converting PFMEA failure modes into Control Plan entries
- Updating an existing Control Plan after a corrective action (8D D7) or process change
- Auditing a Control Plan against a PFMEA to verify alignment
- The user has process flow steps and PFMEA data and needs help structuring the Control Plan
Prerequisites
None required to start. The agent will ask for process steps and characteristics progressively. Ideal inputs (provide if available):
- Process Flow Diagram (list of process steps)
- PFMEA failure modes and current controls
- Drawing characteristics and tolerances
- Special characteristics list (SC, CC, KPC)
Workflow
Step 1 — Gather document information
The agent asks:
- Part number and revision
- Part name
- Supplier / plant name
- Control Plan type: Prototype / Pre-launch / Production
- APQP team members (for the header sign-off section)
Step 2 — Build row by row
For each process step, the agent asks:
- Process step name and number (from the Process Flow)
- Machine, device, jig, or tool used at this step
- What characteristic is being controlled? (product dimension, material property, or process parameter)
- Is this a product or process characteristic? (product = what the part must be; process = how the process must run)
- Is this a special characteristic? — if yes, which classification (SC, CC, ★, ◆, KPC, KCC)?
- What is the specification / tolerance? (nominal ± tolerance, or min/max)
- What gauge or measurement method is used?
- Follow-up: Has an MSA study (Gauge R&R) been performed for this measurement system? If yes, what was the %GRR result? Flag if %GRR > 30% or if no MSA has been performed for a variable SC/CC characteristic.
- What is the sample size? (number of parts per measurement)
- What is the measurement frequency? (every hour, every lot, 100%, first-off)
- What control method is in place? (SPC chart, go/no-go gauge, visual, 100% inspection, statistical sampling)
- What is the reaction plan? (what happens if out of spec or out of control?)
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.
- 7d ago First seen · 141 lines · 95 tokens per session scan A c573ac50ec0b
control-plan-builder is a skill published in the GitHub repository RBraga01/Quality-Engineering-Skills (27 stars, last pushed 3d ago), licensed MIT. It adds 95 tokens to every session and 1,581 once invoked, about $0.0005 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
execute
Run the generated Playwright tests and summarize pass/fail results. Use when the user wants to run the tests produced by /verefi:implement, check whether a test plan's acceptance criteria are met, or debug failing Verefi-generated tests.
llm-eval-testing
When the user wants to design, build, or operate evaluations (evals) for LLM-powered products — chatbots, RAG systems, agents, classification, summarization, structured output. Use when the user mentions "LLM evals," "evals," "RAG evaluation," "RAGAS," "DeepEval," "LangSmith," "LangFuse," "PromptLayer," "OpenAI…
playwright
When the user wants to design, implement, debug, stabilize, or scale Playwright tests. Use when the user mentions "Playwright," "playwright.config.ts," "page.locator," "page.getByRole," "browser context," "fixtures," "test.beforeEach," "trace viewer," "codegen," "Playwright Test," "Playwright MCP," "PWT," "WebKit…
production-testing
When the user wants to design or operate production-side testing — synthetic monitoring, canary analysis, real user monitoring, error-budget-driven testing, shift-right verification. Use when the user mentions "production testing," "testing in production," "TiP," "synthetic monitoring," "synthetics," "Datadog…
security-testing
When the user wants to design, integrate, or operate security testing in their pipeline — SAST, DAST, dependency scanning, secret scanning, container scanning, IaC scanning, fuzzing, authn/authz testing, OWASP coverage. Use when the user mentions "security testing," "SAST," "DAST," "OWASP Top 10," "OWASP ZAP," "Burp…
test-data-management
When the user wants to design or audit how test data is generated, managed, masked, and reset between tests. Use when the user mentions "test data," "test data management," "TDM," "fixtures," "factories," "FactoryBot," "factorybot," "Bogus," "faker," "synthetic data," "data masking," "PII scrubbing," "production…