Instructions file CodexOpenCode
Instructions for morluto/rea, covering repository guidelines, product direction, project structure & module organization, build, test, and development commands and configuration & environment variables.
Skill Claude CodeCodex
Reverse engineer native, managed, Electron/JavaScript, packaged, and browser applications with REA. Use shipped-artifact or approved runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.
MCP server Claude CodeCodexCursor +2
Reverse engineer anything from your terminal or agent with one CLI and MCP server. Runs locally from the rea-agents npm package.
Skill Claude CodeCodex
Audit one bounded Jacobian mathematical slice for missing or unusable executable vocabulary using source demand, catalog composition, contract evidence, and maintained-backend feasibility. Use for proactive gap audits that are broader than one operation but narrower than a repository-wide inventory; do not use for…
Skill Claude CodeCodex
Audit existing MCP tools for execution friction after an agent has reached the tool. Use when reviewing public JSON Schemas, Pydantic validation, operation examples, error recovery, completed agent traces, or benchmark runs to explain malformed calls, retries, or unusable results. Do not use to measure whether agents…
Skill Claude CodeCodex
Audit new or existing Jacobian mathematical operations for public-domain mismatches, hidden work expansion, evidence-backed scale or backend improvements, lossy exact results, source-unbound conclusions, and producer-consumer incompatibility. Use for operation-contract reviews, mathematical performance investigations…
Skill Claude CodeCodex
Decompose a bounded corpus of mathematical proofs, formalizations, scripts, and certificates into recurring solution techniques and the smallest reusable Jacobian postconditions. Use for repository- or corpus-level “what can Jacobian learn?” audits; do not use for one operation contract or one agent trajectory.
Skill Claude CodeCodex
Diagnose whether agents can see, discover, select, and correctly execute MCP tools without conflating those stages. Use when investigating why agents did or did not use an MCP tool, evaluating MCP server instructions or tool descriptions, testing natural-language discovery, or designing a frozen control/treatment…
Skill Claude CodeCodex
Build, validate, and run Jacobian evaluations packaged as Harbor datasets. Use when authoring or changing Harbor tasks, independent verifiers, Oracle jobs, workflow fixtures, task digests, or evaluation handoffs.
Skill Claude CodeCodex
Use when solving nontrivial mathematical problems or investigating conjectures that may benefit from Jacobian's local library of typed operations for exact computation, finite search, structural analysis, formal reasoning, probability, or optimization.
Skill Claude CodeCodex
Review completed or paused mathematical agent transcripts, visible reasoning, code, searches, tool calls, corrections, and final claims to extract evidence-backed lessons for Jacobian operations, discovery, contracts, skills, evaluations, and documentation. Use for mathematical workflow retrospectives and "what should…
Skill Claude CodeCodex
Run source-grounded Jacobian reliability evaluations using recently resolved conjectures as held-out probes. Use for source selection and deduplication, exact input-bound oracles, current-main math.find/math.run contract audits, frozen control/treatment comparisons, observable trajectory scoring, failure attribution…
Skill Claude CodeCodex
Design, audit, and repair fail-closed mathematical verifiers and evaluation contracts, including public schemas, frozen-input binding, task-specific witnesses, diagnostic scoring, adversarial fixtures, and Oracle validation. Use when a verifier can crash, accept malformed claims, reject equivalent witnesses, leak…
Instructions file CodexOpenCode
Instructions for morluto/jacobian, covering jacobian agent guide, what we are building, non-negotiable boundaries, implement mathematics directly and mathematical boundedness is a proof obligation.
MCP server Claude CodeCodexCursor +2
Executable mathematics and independent verification for AI agents. Runs locally from the jacobian npm package.
Instructions file CodexOpenCode
Instructions for morluto/flameox, covering repository guidelines, product direction, project structure & module organization, build, test, and development commands and coding style & naming conventions.
Skill Claude CodeCodex
Use Flameox to investigate runtime performance, memory, execution, scaling, GPU kernels, inference, and reliability with preserved evidence and explicit claim quality.
MCP server Claude CodeCodexCursor +2
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks. Runs locally from the flameox Python package.
Skill Claude CodeCodex
Diagnose, design, implement, and validate system optimizations while treating correctness, retrieval quality, bounded behavior, and avoided downstream work as primary outcomes. Use for performance, latency, CPU, memory, storage, indexing, search, retrieval, caching, batching, concurrency, tokenizer, database, or…
Instructions file CodexOpenCode
Instructions for morluto/leantoken, covering repository guidance, architecture, development, change-specific validation and contributions.
MCP server Claude CodeCodexCursor +2
MCP server "leantoken" as configured in morluto/leantoken. Launched with leantoken.
Instructions file CodexOpenCode
Instructions for morluto/gitcontribute, covering repository working agreements, what we are building, product boundaries, side effects and engineering rules.
MCP server Claude CodeCodexCursor +2
Local-first GitHub contribution research workbench. Runs locally from the gitcontribute npm package.