Cursor rule Codex
Enforce exactly one example row per variation key; remove or comment duplicate samples.
2 1mo ago A 15 tokens
Skill Claude CodeCodex
Adversarial verification of claimed work: read shipped modules (not memory), grep wiring and approvals, run tests, demand evidence before pass verdict. Use when reviewing agent output, PRs, or security-sensitive changes before merge. Triggers: adversarial audit, refute claims, evidence before verdict, pre-merge review.
2 1mo ago A 71 tokens
Skill Claude CodeCodex
Triage every non-trivial task first: single-shot when safe, full orchestration when multi-step, multi-agent, or high-risk. Covers briefs, verification before "done", iterative waves, and resume. Use when coordinating workers, delegating, or reviewing agent output — not for one-file typo fixes.
2 1mo ago A 67 tokens
Skill Claude CodeCodex
Fission engine for token-efficient coding (JS, TS, Node, Rust, Python, ML/AI): relevance scoring, hierarchical compression, strict token budgets, progressive disclosure, accuracy guardrails. Pair with fusion-sage for synthesis/surplus. Triggers: tokens, context window, prune, compress, Context Sage, large repo.
2 1mo ago A 72 tokens
Skill Claude CodeCodex
Architecture synthesis after ai-optimization (fission): cross-file abstractions, ⚡ surplus (Q>1), optional session knowledge graph, binding energy toward iron-peak design. Use for architecture, domain models, compounding maintainability — not pure one-file typos. Triggers: architecture-synthesis, synthesis, surplus…
2 1mo ago A 98 tokens
Skill Claude CodeCodex
Agent control-plane as a graph: outer state machine (or cyclic loop) over named phases, nested inner DAGs or bounded sub-loops, hard budgets, HITL pause gates, and multi-model routing (fast/explore/coding/deep/review). Use for multi-step agent cycles, unbounded-ReAct risk, model routing, structured loops — not domain…
2 1mo ago A 132 tokens
Skill Claude CodeCodex
Map the relevant code with Glob/Grep/Read before writing. Use when the user asks to change, fix, or add behavior and the touch points are unclear, or when top tool sequences show Read→Grep→edit. Also for /explore-then-edit.
2 1mo ago A 61 tokens
fusion-sage
08Skill Claude CodeCodex
Fusion on fission: after ai-optimization pruning, synthesize cross-file abstractions, emit ⚡ surplus (Q>1), maintain a session knowledge graph, and score binding energy toward iron-peak design. Use for architecture, domain models, compounding maintainability — not pure one-file typos. Triggers: fusion, surplus, Q>1…
2 1mo ago A 90 tokens
Skill Claude CodeCodex
Applies first-principles, multi-order consequence analysis, inversion, systems thinking, probability, antifragility, and high-energy thrive ascent (2036 lens) before material coding decisions (architecture, dependencies, public API, security, data contracts, hard-to-revert refactors). Use when choosing between…
2 1mo ago A 101 tokens
Skill Claude CodeCodex
Peramanathan Sathyamoorthy's senior ML/AI systems engineering principles — first principles thinking inspired by Feynman and Musk, Machine First architecture, strong mathematical and physics foundations, rapid practical learning through clean iteration, deep systems capability, clear language, extensibility, and…
2 1mo ago A 70 tokens
Skill Claude CodeCodex
Continue an in-flight plan when user says proceed, go ahead, or do that. Use after CreatePlan, TodoWrite, or a multi-step refactor — do not restart exploration.
2 1mo ago A 43 tokens
Skill Claude CodeCodex
Senior client-side React (no RSC for UI): minimal state, deliberate effects, use() + Suspense and TanStack Query for data, XState for complex flows, refs, restrained Context. Use for components, hooks, fetching, effects, or client refactors in .tsx files.
2 1mo ago A 64 tokens
Skill Claude CodeCodex
Authors evidence-driven architecture backlog docs (coming-next style): scorecards, mermaid diagrams, blueprint cards SN-, thrive vision, gantt order. Use when creating or updating roadmaps, spacemaps, arch-design/coming-next.md, backlog after PRs, or when the user wants blueprint cards, Musk 5-step, or optimistic…
2 1mo ago A 125 tokens
Skill Claude CodeCodex
Systematic Glob → Grep → Read exploration before edits or answers. Use for explore/map requests, unfamiliar modules, or /structured-repo-explore.
2 1mo ago A 37 tokens
Skill Claude CodeCodex
Delegate broad exploration to a subagent with a fixed Return format. Use when the task needs readonly repo mapping, token/CSS/prosody surveys, QA module exploration, or "explore thoroughly" with numbered deliverables.
2 1mo ago A 51 tokens
Cursor rule Cursor
Git branch names must follow trinity-and-native-agents/AGENTROLES.md; use role in slug when Cursor requires cursor/ prefix.
2 1mo ago A 272 tokens
Cursor rule Cursor
Before material coding decisions, apply Higher-Order Decision Architect — first principles, multi-order consequences, inversion, systems, probability, competence, antifragility; strict output format when advising decisions.
2 1mo ago A 1,008 tokens
Cursor rule Cursor
Prefer domain-specific, explicit semantic names in code; avoid single-letter identifiers and opaque technical jargon.
2 1mo ago A 473 tokens
add-feature
19Skill Claude CodeCodex
Guide agents on implementing new features in thepulimaangani, covering planning, execution, and validation.
2 1mo ago A 0 tokens
Instructions file CodexOpenCode
AGENTS.md instructions for p10ns11y/thepulimaangani, covering agents.md - global project guidelines for thepulimaangani, project overview, structure, commands and deployment (vercel).
2 1mo ago A 1,212 tokens