eop-skills

The dealer for a repo-grounded Elevation of Privilege (EoP) threat-modeling game night. Use this skill when the user wants to "deal an EoP deck for <repo>", run an EoP / STRIDE game session against a real codebase, produce a printable or web threat-modeling deck where each card names real files, endpoints, and trust boundaries, or get a dealer's diagram plus a score card to play by the original rules. Trigger on "deal me an EoP deck", "run a threat-modeling game on this repo", "make a STRIDE card deck for our system", or "set up an EoP session". Builds on eop-deck.

Shared foundation for the Elevation of Privilege (EoP) threat-modeling skill suite. Use this skill whenever you need the EoP / STRIDE deck data, need to ground a repo or design against the 74 STRIDE threat cards, need to draw a trust-boundary / data-flow diagram for threat modeling, or need to apply the "would we take a bug for that?" adjudication test. Also use when another EoP skill (eop-deal, eop-referee, eop-sentinel, eop-race, eop-forge) needs the deck or a grounded deck object. Trigger on mentions of STRIDE, Elevation of Privilege, threat cards, trust boundaries, data-flow diagrams for security, or "ground these cards against my code."

The design-time Elevation of Privilege (EoP) skill — threat-model a system before the code exists, and extend the deck with an AI/agent suit. Use this skill to "threat model this design", walk STRIDE against a proposed design, RFC, or architecture sketch and write the threats into the design doc before implementation (shift-left), or to "add the AI suit" — a co-authored seventh suit covering prompt injection, tool/agent abuse, training-data and context poisoning, and over-broad agent permissions (a literal elevation of privilege). Trigger on "threat model this design", "shift-left threat modeling", "model this RFC for security", "walk STRIDE against our design", "add the AI/agent suit", or "threat model our agent/LLM system". Builds on eop-deck; emits an eop-session/1 that eop-referee can turn into backlog.

The adversarial Elevation of Privilege (EoP) skill — race the machine to the novel attack. Use this skill to run a timed contest where the table and an adversarial agent each generate novel exploit hypotheses (Ace-class — the kind with no CVE yet) against a design or repo, blind to each other, then reveal and score: the table scores for threats it names before the agent surfaces them, the agent scores for what it finds first, and the visible speed gap is the lesson. Trigger on "race my design", "race this repo", "beat the machine to the threat", "run an EoP race", or "generate novel attacks against this design on a timer". Builds on eop-deck; hands accepted attacks to eop-referee.

The adjudicator and riff engine for a live Elevation of Privilege (EoP) threat-modeling session. Use this skill during play to rule on a contested threat with the bug-test ("rule on this threat: …"), to unstick a player frozen on an Ace by seeding three novel-attack starting points, to run the 60-second riff variant, or to convert accepted threats into backlog — ticket titles, repro sketches, candidate fixes and tests. Trigger on "rule on this threat", "is this a real threat?", "we're stuck on the Ace", "riff on this", "turn these threats into tickets", or "referee our EoP game". Builds on eop-deck and pairs with eop-deal.

The Elevation of Privilege (EoP) game that never ends — embedded in the pull request. Use this skill to "play a hand" against a diff or PR: pick the highest STRIDE card the change legitimately invites, comment in the card's voice (threat, why-here, candidate fix), and track clean-diff streaks plus a "hardest to threaten" leaderboard so the threat-modeling vocabulary stays alive between sessions. Trigger on "play a hand against this PR", "run the EoP sentinel on this diff", "STRIDE-review these changes", "what threat does this change invite?", or "update the sentinel leaderboard". Builds on eop-deck; complements eop-deal and eop-referee.