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-plangit 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)<a href="https://agentmods.dev/skills/rbraga01/quality-engineering-skills/control-plan"><img src="https://agentmods.dev/badge/skills/rbraga01/quality-engineering-skills/control-plan.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 | $0.00081 | $0.02143 |
| Opus 5 | $0.00041 | $0.01071 |
| Sonnet 5 | $0.00016 | $0.00429 |
| Haiku 4.5 | $0.00008 | $0.00214 |
Grade A, and why
control-plan 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 8d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Control Plan
When to use
Use this skill when:
- Creating a new Control Plan for prototype, pre-launch, or production
- Reviewing an existing Control Plan for completeness and accuracy
- Updating the CP after a process change, corrective action (D7), or PFMEA update
- Auditing a supplier's Control Plan during qualification or an IATF audit
- Linking PFMEA controls to the Control Plan after FMEA review
Prerequisites
- Process Flow Diagram (required — CP must mirror the process flow sequence)
- PFMEA (required — CP controls derive from PFMEA recommended actions)
- Drawing with ballooned characteristics and tolerance data
- List of special and significant characteristics (SC, CC, KPC, KCC)
- MSA results for measurement systems referenced in the CP (for production CP)
Workflow
Step 1 — Determine the CP type
| Type | When | Purpose |
|---|---|---|
| Prototype | During prototype builds | Describes dimensional, material, and functional tests in prototype phase |
| Pre-launch | After prototype, before PPAP | Describes controls in place during pilot/pre-production runs |
| Production | After PPAP approval, at SOP | The living document — updated throughout product life |
All three types may coexist during APQP phases. The Production CP is the one submitted as PPAP Element 7.
Step 2 — Build the Control Plan structure
The CP is a table with one row per characteristic per process step. Each row contains:
Header section (document-level):
- Control Plan number and revision
- Part number and revision
- Part name / description
- Supplier / plant
- Supplier code (OEM code)
- Key contact / phone
- Core team (multi-functional)
- Date (original) and date (revised)
- Customer engineering approval (name/date) — if required
- Customer quality approval (name/date) — if required
- Supplier approval (name/date)
Detail columns (one row per characteristic):
| Column | What to enter |
|---|---|
| Part/process number | Reference number from Process Flow |
| Process name / operation description | Name of the process step |
| Machine, device, jig, or tool | Equipment used at this step |
| Number | Characteristic number (links to balloon drawing) |
| Product characteristic | Product feature being controlled (dimension, material property, appearance) |
| Process characteristic | Process parameter being controlled (temperature, pressure, speed, torque) |
| Special characteristic classification | SC, CC, KPC, KCC, *, ▲ per customer symbology |
| Product/process specification / tolerance | Nominal value and tolerance band |
| Evaluation / measurement technique | Gauge type, method, or test used |
| Sample size | Number of parts per sample |
| Frequency | How often samples are taken (every hour, every lot, 100%) |
| Control method | How the process is controlled (SPC chart, go/no-go gauge, visual, 100% inspection) |
| Reaction plan | What to do if out-of-control or out-of-specification (who, what action, containment) |
What ships with it
1 file 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.
- 8d ago First seen · 203 lines · 81 tokens per session scan A 7333a324c01a
control-plan is a skill published in the GitHub repository RBraga01/Quality-Engineering-Skills (28 stars, last pushed 4d ago), licensed MIT. It adds 81 tokens to every session and 2,143 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
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.
ai-augmented-testing
When the user wants to evaluate, adopt, or operate AI-augmented testing tools and approaches — autonomous test generation, self-healing locators, AI-assisted authoring, vision-based testing, agentic test runners. Use when the user mentions "AI testing," "AI-augmented testing," "Testim," "Mabl," "Functionize,"…
ci-test-orchestration
When the user wants to design, audit, or optimize how tests run in CI — sharding, matrix builds, parallelism, retry policy, test selection, artifact handling, and gate strategy. Use when the user mentions "CI test orchestration," "test sharding," "matrix builds," "parallel tests in CI," "GitHub Actions matrix,"…
cucumber-gherkin
When the user wants to design, implement, debug, or evolve BDD scenarios using Cucumber and the Gherkin syntax across any language (Java, JS, Ruby, JVM, etc.). Use when the user mentions "Cucumber," "Gherkin," "Given/When/Then," ".feature file," "step definitions," "scenario outline," "data tables," "Cucumber hooks,"…
junit-testng
When the user wants to design, implement, debug, or optimize JUnit 5 (Jupiter) or TestNG tests on the JVM. Use when the user mentions "JUnit 5," "JUnit Jupiter," "@Test," "@ParameterizedTest," "@MethodSource," "@TestFactory," "TestNG," "@DataProvider," "@BeforeEach," "@BeforeMethod," "AssertJ," "Hamcrest," "Mockito,"…
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…