vinilana

vinilana/dotcontext

Instructions file CodexOpenCode

Instructions for vinilana/dotcontext, covering dotcontext agent instructions, architectural intent, repository references, expected validation and mcp install changes.

vinilana/dotcontext

Instructions file

Instructions for vinilana/dotcontext, covering dotcontext repository guide, source of truth, working boundaries, current priorities and validation commands.

vinilana/invokta

Skill Claude CodeCodex

Review Invokta contracts for public APIs, acceptance criteria, errors, invariants, operational limits, compatibility, and architectural boundaries. Use before implementing or approving changes to interfaces, schemas, ports, events, observable persistence, configuration, or public behavior in this repository.

vinilana/invokta

Skill Claude CodeCodex

Deliver Invokta milestones and work items with TDD, adherence to versioned contracts and architecture, complete validation, and one cohesive commit per work item. Use when developing features, fixing bugs, executing roadmap milestones, or completing acceptance criteria in this repository.

vinilana/invokta

Skill Claude CodeCodex

Prepare Invokta versioned releases on dedicated release branches with synchronized package metadata, changelog and validation evidence, complete repository gates, and one cohesive commit. Use when asked to prepare, cut, stage, or validate an Invokta release or release candidate.

vinilana/invokta

Instructions file CodexOpenCode

Instructions for vinilana/invokta, covering repository instructions, language and delivery workflow.

vinilana/invokta

Instructions file

Instructions for vinilana/invokta, a project described as: A TypeScript framework for reusable domain AI capabilities across direct, CLI, and MCP transports.

vinilana/invokta

Skill Claude CodeCodex

Add or change domain capabilities in this Invokta Action Engine with explicit contracts, authenticated access, engine-owned dependencies, migrations, and tests. Use when a user asks to add an action, tool, capability, domain behavior, repository operation, schema, or capability ID, or to expose behavior consistently…

vinilana/invokta

Skill Claude CodeCodex

Deploy, upgrade, verify, or roll back this Docker Compose MCP OAuth stack on a VPS, including Hostinger environments with an existing Traefik proxy and hosts that use bundled Caddy. Use for production releases, new VPS setup, image rebuilds, environment configuration, database backup, owner bootstrap, health checks…

vinilana/invokta

Skill Claude CodeCodex

Develop this generated Invokta Action Engine when changing capabilities, dependencies, tests, or its direct invocation, CLI, MCP stdio, and MCP HTTP channels. Use for implementation, refactoring, debugging, and contract review in this project.

vinilana/invokta

Skill Claude CodeCodex

Diagnose, test, and change the self-hosted OAuth layer for this MCP service while preserving PKCE, DCR, ES256 tokens, rotating refresh tokens, secure consent, sanitized logs, and fail-closed resource authentication. Use for OAuth login or consent failures, Gemini connection problems, DCR metadata errors, token…

vinilana/invokta

Agent

Use for complex multi-file development, migrations, and long-horizon implementation that requires sustained verification.

vinilana/invokta

Agent

Use for reproducing failures, isolating root causes, and implementing evidence-backed regression fixes.

vinilana/invokta

Agent

Use for API documentation, guides, examples, ADR updates, and other source-grounded documentation work.

vinilana/invokta

Agent

Use for implementation planning, dependency analysis, and acceptance-criteria design before code changes.

vinilana/invokta

Agent

Use for runnable spikes and prototypes that test one product or technical assumption quickly.

vinilana/invokta

Agent

Use for read-only review of diffs, contracts, security boundaries, and regression risks.

vinilana/invokta

Agent

Use for narrow, well-specified development tasks with limited files and obvious validation.

vinilana/invokta

Cursor rule

Route development work through the versioned Cursor agent routing engine before delegating to a custom subagent.

vinilana/anyharness

Agent Claude Code

Time de 7 subagents especializados pra desenvolver o Harness MCP. Cada agente é dono de um bloco da SPEC.md.

vinilana/anyharness

Agent Claude Code

Use proactively when starting new components, making cross-cutting tech decisions, resolving conflicts between subsystems, or whenever a change touches more than one module of anyharness. Owns coherence with SPEC.md, the positioning vs @dotcontext/cli, and the design principles in §5.

vinilana/anyharness

Agent Claude Code

Use when designing or implementing Contracts — Specs, Tasks, contract.spec.validate, contract.task.next, contract.task.complete, the resource handler for harness://contracts/specs/{id}, or anything in src/contracts/ and .harness/contracts/. Owns the behaviour harness layer defined in SPEC §10.

vinilana/anyharness

Agent Claude Code

Use when implementing judge.list, judge.review, the Anthropic-backed inferential runner, rubric prompt management, output JSON validation, fixture regression, or anything in src/judges/ and .harness/judges/. Owns the inferential feedback side defined in SPEC §3, §4, §7, §9.

vinilana/anyharness

Agent Claude Code

Use when implementing or modifying the MCP server core — stdio transport, capabilities declaration, tool/resource/prompt registry, request handlers, file watcher wiring, error envelopes, or anything in src/server/ and the cross-cutting plumbing. Owns the surface defined in SPEC §3 and §4.