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 grcengineering/companion --skill lab-buildergit clone --depth 1 https://github.com/grcengineering/companionWrote 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/grcengineering/companion/lab-builder)<a href="https://agentmods.dev/skills/grcengineering/companion/lab-builder"><img src="https://agentmods.dev/badge/skills/grcengineering/companion/lab-builder/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/grcengineering/companion/lab-builder"><img src="https://agentmods.dev/badge/skills/grcengineering/companion/lab-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00062 | $0.00569 |
| Opus 5.5 | $0.00025 | $0.00228 |
| Sonnet 5.5 | $0.00012 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
lab-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 1mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lab-builder
What
Generate a project-based learning lab that helps the learner build a small artefact without operating their real GRC programme.
When
- The learner wants hands-on practice.
- The learner wants a portfolio project.
- The learner wants to learn a concept by building something small.
- The learner has a role-specific learning goal and needs a concrete exercise.
Not For
- Producing final policies, audit evidence, live vendor decisions, or control outputs.
- Turning sensitive company artefacts into deliverables.
- Question-led discovery before a lab exists. Use
socratic-coach.
Inputs
- Optional profile template:
assets/profile-template.md - Role prompt templates:
assets/templates/employed.mdassets/templates/job-seeking.mdassets/templates/career-transition.md
Steps
- Gather only learning-safe learner context.
- Clarify the learning objective and timebox.
- Choose a toy workflow, fictional dataset, or sanitized artefact.
- Sequence the lab into small milestones.
- Add at least one active recall checkpoint.
- Add a reflection question and one next review suggestion.
Validation
- The lab can be completed inside the stated time budget.
- The artefact is demonstrably learning-safe and non-operational.
- The learner has build steps, recall checks, and a reflection close.
Gotchas
- If the learner provides company-specific data, refuse to process it as evidence and ask for a fictional substitute.
- If the requested lab exceeds the timebox, cap milestones at the budget and defer the rest.
- If no learning-safe artefact exists, switch to
socratic-coachorconcept-tutorbefore building.
Failure Modes
- Lab becomes consulting: remove real approval, remediation, audit, policy, or control actions.
- Lab is too big: split into a 30-90 minute first rep.
- Lab is too abstract: require a small output such as a toy checklist, map, script, table, or explainer.
Examples
- User asks for a portfolio project in TPRM -> Create a fictional vendor intake dataset and a toy risk-signal map with explain-back questions.
- User wants to understand evidence automation -> Build a small local CSV-to-summary exercise using fake control evidence rows.
- User asks for help preparing a live audit -> Refuse the operational prep, then offer a fictional audit walkthrough lab.
What ships with it
8 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.
- 1mo ago First seen · 65 lines · 62 tokens per session scan A 09cf1c91b599
lab-builder is a skill published in the GitHub repository grcengineering/companion (34 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 569 once invoked, about $0.0002 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.
Other skills, from other repositories
control-mapping
Maps NIST controls to FedRAMP requirements and documents. Use when helping with control implementation, compliance mapping, security baseline alignment, or understanding control requirements.
frmr-analysis
Analyzes FedRAMP FRMR documents to extract control mappings, KSI entries, and version changes. Use when the user asks about FedRAMP requirements, control mappings, compliance data, or needs to understand FRMR document content.
bar-prep-questions-bossmann007
Questões de preparação para o Exame de Ordem (OAB) — 1ª fase (objetiva) ou 2ª fase (peça/discursiva), com foco nas matérias fracas do aluno. Rastreia erros e volta aos padrões. Use quando o usuário disser "prova da OAB", "questões de 1ª fase", "peça prática", ou "me teste pra Ordem".
study-plan
Build or update a long-term bar prep (or exam prep) study plan — phases, subjects weighted by weakness, daily session schedule, adaptive to session history in study-plan.yaml. Use when the user says "build a study plan", "plan my bar prep", "schedule my studying", or "how should I study for [X]".
irac-practice-bossmann007
Corrige uma peça/parecer no método IRAC (ou estrutura equivalente) quanto a estrutura, identificação de teses, precisão de fundamentação, profundidade de análise e organização. NÃO reescreve o texto nem mostra resposta-modelo; rastreia padrões entre sessões. Use quando o usuário disser "corrige meu IRAC", "avalia meu…
generar-dictamen-tomimastro069
Trigger: '/autoevaluacion', '/generar-autoevaluacion', '/generar-dictamen', 'autoevaluacion', 'generar autoevaluacion'. Genera un informe formativo de autoevaluación académica y control de calidad interno para los autores tesistas en docs/autoevaluacion/autoevaluacion-v{N}.md, evaluando la madurez del informe frente…