content engine · skills, orchestrator, agents

Cywareness Simulation Archive

Production security-awareness content at volume, and the pipeline that now builds it.

status 2025 to 2026 · body of workrole designed + built end to end
Cywareness Simulation Archive: One lure, four difficulties, rendered by the real pipeline. Read across: the cle
One lure, four difficulties, rendered by the real pipeline. Read across: the clean control, then a shifted date, then an invented same-day deadline and a wrong department name, then an explicit 24-hour threat and an altered postal code. The platform adds one automatic sender flag on top of the authored ones.
Cywareness Simulation Archive: The reviewer sheet the pipeline writes for every sim: each planted flag highligh
The reviewer sheet the pipeline writes for every sim: each planted flag highlighted, named, and paired with the teaching text the trainee sees after they click.
recorded run
The real system running in the terminal: skills, the orchestrator contract, an agent, and a real indicator sheet and ZIP built from one sim.
What it solves

Hand-authoring calibrated sims across brands, languages, and tiers stopped scaling somewhere in the hundreds. The pipeline's split matters for maintenance: the deterministic Python packagers produce byte-identical output run to run, while the model-driven agents are the only part that improves when a better model ships. One named seam, one place to upgrade.

Who it serves

A security-awareness platform producing sims across many brands and markets.

Who it is for

The depth behind the sim production line above.

How it works
  1. Skills hold the rulesClaude Code skills encode the indicator rules, tier spreads, and the sim-pipeline contract.
  2. The orchestrator runs the contractAn eight-step orchestration turns one brief into a full tiered package.
  3. Agents do the judgmentSub-agents author the tiers and the indicator realism, the part that is genuinely hard.
  4. Python packages it, deterministicallyIndicator sheets and upload ZIPs are built by Python that does not change run to run.
  5. Upgradeable at the seamOnly the model-driven agents get better with a better model. The Python packagers stay byte-for-byte identical. Now that Fable 5 exists, the indicator-realism agent is the highest-upside swap.
Built with
Claude Code skills orchestrator sub-agents Python packagers tsim CLI