lebobo88

Screenshot-first visual end-to-end validation policy for browser-rendered UI and webview jobs after verifier approval.

Default engineering workflow. Classify a technical request, route it through the native T1/T2/T3 engineering fleet, and return only independently verified completion to the orchestrator.

Safely operate Claude Code's opt-in advanced capabilities—sessions, worktrees, agent teams, Skills, MCP, plugins, hooks, Channels, schedules, goals, and Agent SDK integrations—when the user explicitly asks for one. Do not use for an ordinary build request.

Routes selective local Codex plan, code, verification, and visual judgment with evidence-backed blocking and strict cost caps.

Shared evidence, accessibility, context, and handoff rules for the local design-agent fleet.

Produces contextual creative theses and bounded visual directions without generic model defaults.

Creates one disposable selected-direction prototype under the isolated design prototype root.

Independently reviews design packets for evidence, coherence, accessibility, completeness, specificity, and engineering readiness.

3D modeling and DCC (Blender) pipeline standards for the Arcade crown (The Sculptor). Produces geometry execution standards — topology / edge-flow rules, retopo targets, UV / lightmap layout, PBR channel sets, LOD chains, pivot/scale/axis conventions — and the Blender/DCC commission contract that garland's blender-model / blender-rig sub-agents execute via the existing blender-mcp backend. The crown never models, retopologizes, or drives Blender inline; it writes the DCC contract and emits an ASSET_JOB (model_type:mesh|rig, provenance_required:true) to garland. Ties to the mesh-topology-budget gate and (for gen-AI assets) ai-content-provenance.

Production rigging, skinning, and animation pipeline standards for the Arcade crown (The Choreographer). Captures Blender/DCC industry standards — armature architecture (single root, .L/.R, roll), FK/IK + pole + FK/IK switching, LBS vs DQS skinning, automatic/heat/voxel weights with normalization (<=4 influences, sum=1), corrective shape keys, mocap retargeting, NLA action libraries, gimbal-lock QC, and cross-engine export (Unreal / Unity Humanoid / USD). The crown specs the rig/anim contract; it never rigs, skins, or produces binaries — rig/anim implementation -> engineering (pp tech-animator) via DEV_TASK, bespoke motion/mocap + Blender rig execution -> garland (blender-rig) via ASSET_JOB. Ties to the rig-quality gate; deformation-ready topology comes from The Sculptor (game-3d-modeling-and-dcc).

The end-to-end RLM-Gaming production pipeline and delegation contract. Read this before orchestrating any multi-discipline game workflow. Defines the five-layer studio flow, which work the Arcade crown owns vs delegates, the exact cross-squad envelopes (PRD/DEV_TASK → engineering, CREATIVE_BRIEF/SHOT_LIST/ASSET_JOB → garland), the HITL control points, and the phase/gate map. Invoked by The Director and The Producer.

Runtime NPC AI DESIGN for the Arcade crown (The Puppeteer). This is the design side of in-game enemy/NPC behavior — pattern selection (FSM/BT/GOAP/Utility/HTN/EQS/ML-Agents), blackboard key design, perception modules, and NavMesh strategy — NOT generative AI and NOT runtime code. Read before authoring any AI tuning targets in an encounter_design_doc or before emitting a DEV_TASK for AI work. The crown specs; pp game-ai-programmer implements.

Art and audio DIRECTION for the Arcade crown (The Artisan + The Conductor). Produces the style bible, reference boards, LOD/poly/texture/material budgets, and the audio mix-tier sheet, sonic palette, and Wwise/FMOD event map — then COMMISSIONS the actual binaries from garland via CREATIVE_BRIEF/ASSET_JOB/SHOT_LIST with provenance_required:true. The crown never generates images, audio, or 3D inline. Ties to the ai-content-provenance rubric (garland C2PA-signs every gen-AI asset).

The Arbiter's age-rating and platform-certification skill for the Arcade crown. Read this before producing any content-disclosure inventory, IARC answer map, target-rating feasibility study, per-platform TRC/cert checklist, regional-edit plan, or cert-submission package. Covers ESRB/PEGI/IARC/CERO/USK/ClassInd ratings, platform cert (PlayStation TRC, Xbox XR/XGSP, Nintendo Lotcheck, Steamworks + Deck-Verified, Apple/Google review), and CVAA accessibility law. Produces disclosure/feasibility/checklists only — code fixes go to engineering (game-cert-team), assets to garland. Escalates IP/law questions to legal-compliance (Senate/curia) via HANDOFF.

Economy-designer skill for producing economy simulations and monetization specs — currencies, source/sink/leak tables, gacha/loot math with pity timers and published odds, Monte-Carlo balancing, progression curves, retention/LTV/ARPDAU KPIs, store A/B plans, and a per-region jurisdiction table. Read this before designing any monetized or live-service economy. Invoked by The Economist and The Arbiter; feeds the loot-box-jurisdiction gate. Complements the engineering-side game-design economy-spreadsheet template in pair-programmer by adding Monte-Carlo balancing, the full jurisdiction matrix, and KPI dashboards.

THE deep cross-engine reference for the Arcade crown. Read this before any engine-selection decision or per-engine tech-design checklist. Covers conventions, asset/data patterns, runtime AI, netcode, perf tooling, and build/cert path for Unity, Unreal Engine 5, Godot, Web (Babylon.js/Three.js/Phaser/PlayCanvas), Spring/Recoil RTS, and custom engines — plus when to pick which. Owned by The Forgemaster; maps to the pair-programmer game-dev-unity/unreal/godot/web/custom profiles. Produces selection matrices and tech-design checklists only — implementation is a DEV_TASK to engineering. Always pins perf claims to the game-perf-budget rubric tiers.

Five named aesthetic bundles (Ethereal Glass, Editorial Luxury, Soft Structuralism, Minimalist Editorial, Industrial Brutalist) with surface / typography / motion / texture specs and a profile-to-archetype decision matrix.

Canonical CreativeBrief markdown + JSON schema, aligned 1:1 with Hydra CreativeBrief envelope. Sections cover vision, references, aesthetic, technical approach, key shots/messages, production, guardrails, approvals.

HITL gate catalog, audit-log shape, DecisionRecord schema, three-lines-of-defense mapping, v1 gate IDs (brand-consistency, regulated-claims-review, budget-cap, attribution-soundness, ip-clearance).

Audience segmentation toolkit — RFM, behavioral cohorts, JTBD, ICP for B2B, CDP/CRM integration patterns, persona archetype templates.

Brand safety and regulated-claims rulebook — toxicity/bias categories, FDA/FTC/FCA/GDPR rules, prohibited-content registry, brand-guideline enforcement, HITL escalation matrix, verdict schema.

Six industry-specific campaign playbooks — funnel stages, KPI targets, channel mix, cadence, critical gates, failure modes, blueprint examples.

Experimentation toolkit — A/B test design, sample-size from MDE+power, MAB, sequential testing, causal inference (DiD/synth-control/RDD), pitfalls, reporting template.

Onboarding, retention, and winback playbooks — cadence templates, behavioral triggers, frequency rules per industry, sunset/suppression rules.

Offline A/B experimentation for prompt/policy/skill/rubric variants: defines what constitutes an experiment, the offline-only rule, the scoring contract, the anti-Goodhart + safety-floor constraints, the statistical-honesty rule, and the governance wiring into the TheEights evolution loop.

Encoded policy constraints: refunds/disclosures/consent, GDPR/CCPA data-minimization themes, right-to-human mandates, regulated-claim language rules, AI-disclosure requirements. Consumed by Harmonia, Soteria, Hermes, Eunomia.

The structured state token that travels with the customer across every agent handoff — identity ref, goal, active objects, constraints, sentiment, history digest. Minted by Iris; carried inside HANDOFF payloads.

Hard budgets, bounded loops, and the four terminal states. Step/dispatch/retry ceilings per command, graph-level termination conditions, and cost-tiering rules. Owned by Hestia.

The KPI frame: containment, FCR, AHT, CSAT-proxy, escalation precision/recall, cost-per-resolution, SLA attainment — and the Agent-Manager dashboard contract over events.jsonl. Owned by Hestia; consumed by Themis, Soteria, Echo.

Intent/language/sentiment/priority classification and routing rules for incoming support tickets. Owned by Iris; consumed by Hestia for dispatch.

The crawl/walk/run rollout discipline: phase definitions, promotion criteria (containment, hallucination rate, redaction record), demotion triggers, and the shadow-mode contract. Owned by Hestia; drives /support-shadow.

Sentiment tracking and style adaptation with anti-manipulation guardrails: acknowledgement patterns, register matching, de-escalation sequences, and the read-back test. Owned by Harmonia; consumed by Iris, Soteria, Themis.

Templates and risk-tier evolution policy for authoring new agents, skills, and hooks — the 3 artifact kinds this harness produces (no "mcp" kind; this harness has no MCP). Used primarily by meta-agent when extending the harness. Auto-invocable.

Reference-only skill documenting where artifacts live, the 3-verdict vocabulary (pass/pass-with-notes/reject), and the Preserved-Invariants-vs-Changed-Behaviors contract for revising an existing artifact. Load before writing or revising any artifact under .fable/. Auto-invocable.

Show CONSTITUTION.md's content and invariant list on request, re-run the SHA-256 hash check against CONSTITUTION.sha256 on demand, and document the amendment procedure. Useful for Claude to consult proactively as well as for a user to invoke directly.

Merge-safe installer that makes FABLE-HARNESS's agents/skills/hooks available at Claude Code's user scope (~/.claude), so they work across every project, not just H:\FABLE-HARNESS. Manual-only — never auto-invoked, since this touches shared, hard-to-reverse state outside this project.

Canonical model-tier reference and the Fable-5 manual-only enforcement protocol. Consult before writing or changing any model field (agent frontmatter, skill frontmatter, Task dispatch parameter, settings.json availableModels, env vars). Auto-invocable — any agent or skill authoring a new artifact should load this first.

Highest-stakes planning skill using Fable-5. Manual-only — Claude can never auto-invoke this; only a user typing /plan-deep can. Use for the small number of asks big enough to warrant Fable-level structure and thinking budget (major-scope architecture, cross-cutting rewrites, irreversible decisions).

Everyday, auto-invocable planning skill for routine feature/bug/refactor work. Sonnet-tier — the non-Fable default. Use for most planning needs; escalate to /plan-deep (manual-only, Fable-5) only for the rare highest-stakes plan.

Run one of the 10 standing governance-forum reviews (taxonomy_blueprint.md Section 8.2 — discovery, scope, design, architecture, api_contract, threat_privacy, test_readiness, release_readiness, incident_postmortem, service_review) over an existing artifact or change. Auto-invocable when a user asks for a focused review pass rather than new production. The actual orchestration lives in .claude/workflows/review.js, invoked here via the Workflow tool.

Shared audio production protocol for the Helios sub-crew — foley, score, and dialogue. Spectral allocation, sync, stems, loudness, and mix manifests. Owned by Helios.

Curated comfyui workflow recipes Helios fires via the hydra-creative.comfyui.* MCP tool. Each recipe lists input schema, output, when-to-use, and cost.

CreativeBrief envelope contract, intake template, and validation checklist for Calliope and any head receiving strategic intent.

ShotList schema authoring, camera and lens grammar, pacing rules per channel. Owned by Helios.

IP clearance checklist and brand-guardrail rubric. Owned by governance-c2pa, consumed by Calliope and Helios.

Euterpe's paid-acquisition playbook. ROAS targets, bid strategies, fatigue detection, scale vs rotate decisions, CAC payback heuristics.

LUTs, white-balance, mood-driven grading, and color-space deliverable mapping. Helios uses this to brief comfyui and color sub-pipelines.

Pillar to cluster to repurpose cadence. Polyhymnia's playbook. Atomic-unit framework.

Cato's instruments — board memo and resolution formats, minutes discipline, fiduciary-duty analysis frames (care/loyalty/BJR), committee charter skeleton, delegation-of-authority matrix, conflict screens, and board-grade AI-oversight reporting.

Tribonian's pipeline — verification tiers, authority ranking, jurisdiction and temporal tagging, the fabrication-breach protocol, and the honest statement of Phase-1 limits (no live legal databases). Enforces Table III: no fabricated citations, ever.

Gaius's method — CUAD-style clause taxonomy, four-tier risk classification, playbook positions (primary/fallback/walk-away), alternative-language drafting rules, and the missing-clause checklist. Drives /contract-review and all commercial paper.

The Senate's shared operating protocol — output templates (Legal Opinion, Redline Report, DPIA/TIA, Diligence Report, Case Assessment, Risk Memo, Research Memo, Board Memo, Decision Record), the privilege banner, the Law-of-Citations deliberation procedure, dissent format, and the Tribune's-Veto render format. Every Senate output conforms to a template here.

Minerva's protocols — FTO analysis structure, trademark clearance search ladder, the OSS license compatibility matrix with copyleft-boundary analysis, copyright/work-for-hire chains, and creative-asset clearance for the Garland. Search before clearing; epistemic status always stated.

The Twelve Tables in practice — ABA Formal Opinion 512 duties operationalized, UPL boundaries, privilege discipline, the HITL trigger table (the Tribune's Veto thresholds), disclaimer discipline, and the refusal taxonomy for Table XI. Every jurist carries this skill's constraints.

The Curia's cognitive stack — IRAC decomposition, multi-hop norm application, analogical and counterfactual checks, chain-of-verification, and confidence scoring with HITL escalation thresholds. Every jurist reasons through this skill.

Cicero's kit — claim triage with deadline discipline, elements-vs-evidence method, privilege handling and litigation holds, procedural posture mapping, settlement decision trees with shown EV math, and e-discovery scoping basics.

AI governance — EU AI Act Article 9, NIST AI RMF, ISO/IEC 42001 — risk classification, lifecycle gates, model cards, HITL policy, AI incident response.

Crisis response toolkit — classification, trigger thresholds, escalation tiers, war-room activation, rapid liquidity stress, supply-chain alternate-source, holding-statement, AAR.

Adversarial red-team debate protocol — when to use it, the 4-step structure, role-pair recipes, Referee scoring, termination conditions, MAS failure mitigations.

Enterprise risk management — COSO ERM 2017 + ISO 31000 — risk taxonomy, appetite statement, top-risk register, KRIs, Bow-Tie, three-lines-of-defense.

Enterprise executive decision frameworks, memo templates, board protocol, RACI, OKR, escalation rules, dissenting-opinion format.

Deterministic financial tools — WACC, NPV, IRR, payback, EVA, real-options, Monte Carlo, sensitivity, covenant/liquidity checks. The Financial Hardcoding Directive.

M&A playbook — deal thesis, screening, financial/commercial/legal diligence, valuation methods, real-options on deal structure, integration playbook, post-deal KPIs.

Scenario planning toolkit — 2x2 matrices, four-case canvas, Monte Carlo setup, sensitivity & tornado, decision-tree EV, war-game, reverse stress test, optionality scoring.

Tiered cross-vendor vs same-vendor judge policy. Read this before invoking any judge so the gate is enforced correctly. Loaded on demand by the `pair-programmer` skill. Authoritative source is `mcp__pp_harness__gate_eligible_judges`; this document explains why the policy is the way it is.

Master skill for the pair-programmer harness. Loaded by every /pp:* slash command. Defines the full Phase-11 request lifecycle — triage, profile snapshot, taxonomy mapping, judge routing with cross-vendor policy, Reflexion ×1, missability gate, master-plan patching, and run finalization. Read this before driving any harness run.

How `<project>/.harness/profile.yaml` modifies gates. Loaded by the `profile-loader` agent and referenced by the master skill. On first run, the harness detects the project type and writes profile.yaml after a one-line confirmation; only an explicit `skip` (or pre-existing absent file the user opts not to bootstrap) leaves the run in generic mode.

File layout under `<project>/.harness/<run_id>/` and the kinds of artifacts produced by each stage. Loaded on demand by the `pair-programmer` skill. Every file written under .harness/ MUST go through `mcp__pp_harness__archive_artifact` UNLESS it lives inside an active best-of-N candidate worktree (those files are tracked via git inside the worktree, not via the artifacts table).

Skill for producing distinctive, professional-grade game-design artifacts (GDD, mechanic specs, level greybox, narrative bibles, economy spreadsheets) that avoid generic AI aesthetics and standard "explore a world / engage in combat / build relationships" pitfalls. Invoked by spec-author, narrative-designer, level-designer, encounter-designer, economy-designer when the active profile is in the game-dev family.

Protocol for the `master-plan-patcher` and `run-finalizer` agents. The per-project `<project>/PROJECT_MASTER.md` follows the Section 9 20-section template. Every successful run patches the relevant sections with cross-references to the run's artifacts.

How to invoke a rubric and emit structured rubric scores. Loaded by judge agents. The 13 standard-aligned rubrics live in the daemon registry; mirror copies under `.claude/rubrics/<id>.md` are generated via `pp-daemon dump-rubrics`.

Reusable policy text the master skill injects into every stage. Every task maps to ≥1 of the 16 taxonomy sections. Trivial tasks reduce to a changelog entry; standard tasks produce required artifacts; major tasks invoke a team. Loaded on demand by the `pair-programmer` skill.

Templates for the 8 artifact kinds (agent, skill, command, hook, team, squad, rubric, mcp) across the 6 sibling projects. Location conventions, frontmatter, validators, default risk class.

Known drift, injection, and runaway patterns plus mitigations. Reference before logging a Smith anomaly or wiring a detector.

The 10 immutable invariants (N1..N10) that AgentSmith enforces across the AI ecosystem. Reference before any refusal, override, or constitutional citation.

How AgentSmith isolates rogue artifacts and agents. Detect, suspend, sandbox, file HITL, await ruling, reinstate or purge. Includes what must NEVER be quarantined.

Refusal-appeal protocol between AgentSmith and Hydra's venom gate. How to file false-positive or false-negative appeals, immortal-head review path, and required audit trail.

Shared conventions across the 6 sibling AI projects. Frontmatter, .claude layout, team and command schemas, hook patterns, MCP registration, artifact directories. The default-when-unsure reference.

The propose/evaluate/commit/HITL contract with TheEights for evolving artifacts. Maps risk_class to evolution policy and documents the API surface AgentSmith calls.

When and how AgentSmith spawns replicator clones, the per-scope quota of 4, trigger conditions, and teardown rules. Read before any /smith:replicate invocation.

Memory fabric usage — ephemeral / episodic / semantic. Read this before reading from or writing to Hydra memory.

Per-workflow budget enforcement: tripwire at 80% (downgrade model tier), HITL at 100%. Telemetry pattern for cost-per-task tracking.

How to construct, validate, and route Hydra's typed cross-squad message envelopes. Use whenever an agent emits or consumes a CSuiteDecisionPacket, PRD, ArchRFC, DevTask, CreativeBrief, ShotList, AssetJob, HITLRequest, DecisionRecord, or Handoff.

When and how Hydra pauses for human input. Defines HITL gate placement, render format, resume contracts, expiry behavior, and override semantics.

How Hydra discovers, resolves, and routes to squad packs. Read this before adding/removing/modifying a squad.

Nightshift planning meta-skill — turns a rough idea into a standardized, verifier-ready spec in specs/. Use whenever the user asks to plan, spec, or queue work for the nightshift factory.