gustavo-meilus

gustavo-meilus/superpipelines

Agent

Use when the parity-test-a pipeline needs to format the reader's key-value data into a human-readable summary text file.

gustavo-meilus/superpipelines

Agent

Use when the parity-test-e pipeline needs to read a changelog markdown file and extract per-version breaking changes and new features for the formatter step.

gustavo-meilus/superpipelines

Agent

Use when the parity-test-e pipeline needs to render a concise markdown release summary from extracted changelog entries produced by the extractor step.

gustavo-meilus/superpipelines

Agent

Use as the second tracer step to verify the writer's sentinel output. Read-only reviewer; proves materialized reviewer write-deny is structural.

gustavo-meilus/superpipelines

Agent

Use as the first tracer step to write a known sentinel string to the run dir as proof the data-only dispatch path executed.

gustavo-meilus/superpipelines

Skill Claude CodeCodex

Use when the user wants to run the parity-test-g pipeline on Tier 2 (Cursor/Windsurf/Cline) to tokenize a markdown file and produce a top-20 word frequency report.

gustavo-meilus/superpipelines

Skill Claude CodeCodex

Loaded by the run-parity-test-g entry skill to supply operating protocol and invariants for markdown tokenization and word frequency counting in the parity-test-g pipeline. Not user-invocable.

gustavo-meilus/superpipelines

Skill Claude CodeCodex

Use when the user wants to run the parity-test-h pipeline on Tier 2 (Cursor/Windsurf/Cline) to validate a YAML config file and produce a structured markdown validation report.

gustavo-meilus/superpipelines

Skill Claude CodeCodex

Loaded by the run-parity-test-h entry skill to supply operating protocol and invariants for YAML config validation in the parity-test-h pipeline. Not user-invocable.

gustavo-meilus/superpipelines

Instructions file CodexOpenCode

Instructions for gustavo-meilus/superpipelines, covering superpipelines agent onboarding, project purpose, stack and runtime, build, test, run and architecture map.

gustavo-meilus/superpipelines

Instructions file

Instructions for gustavo-meilus/superpipelines, a project described as: Loop Engineering for AI coding agents, with real review boundaries. Your AI reviewer cannot edit code. Structurally.

gustavo-meilus/superpipelines

Instructions file Gemini CLI

Instructions for gustavo-meilus/superpipelines, covering superpipelines — antigravity cli 2.0 context, what this plugin does, commands, antigravity-specific paths and migration from gemini cli.

gustavo-meilus/superpipelines

Agent

Use when designing a new multi-agent pipeline, generating spec/plan/tasks/topology artifacts, adding a step to an existing pipeline, updating a step, deleting a step, creating a single subagent definition, or diagnosing a pipeline topology failure.

gustavo-meilus/superpipelines

Agent

Use when auditing existing pipeline bundles, agent files, or skills against superpipelines v2 layout, frontmatter, topology, and runtime-safety standards. Invoked automatically after new-pipeline, new-step, update-step, and delete-step. Produces severity-classified reports (SEV-0/1/2/3) with cited file:line evidence.

gustavo-meilus/superpipelines

Agent

Use during a Pattern 3 iterative loop after a tester reports failures, before dispatching a fixer — diagnoses whether failures are fixable bugs or architectural problems, detects "fixes reveal new failures in new locations" pattern, and decides whether to continue or escalate per Pattern 3 protocol.

gustavo-meilus/superpipelines

Agent

Use when surveying an existing pipeline bundle for optimization opportunities — topology merge/split/parallelize/reorder, model-tier right-sizing, past-run pain signals, and protocol-quality advisories. Dispatched read-only by optimizing-a-pipeline; renders an opportunity report for the orchestrator to persist. Never…

gustavo-meilus/superpipelines

Agent

Use as Stage 2 review ONLY after pipeline-spec-reviewer returned PASS — checks code quality, idiom, maintainability, naming, structure, and tests against the spec. Refuses to run if Stage 1 not yet PASSed. Read-only; never edits.

gustavo-meilus/superpipelines

Agent

Use as Stage 1 review after a pipeline-task-executor produces output — checks ONLY whether the output matches the spec exactly. Under-build AND over-build both FAIL. Stage 2 (code quality) cannot begin until this passes. Read-only; never edits.

gustavo-meilus/superpipelines

Agent

Use when implementing exactly ONE task from a tasks.md file as part of a Pattern 5 (SDD) parallel implementation phase, or when a single bounded implementation task needs a fresh-context worker. Receives extracted task text plus spec/plan paths; performs the task; self-verifies; emits terminal status.

gustavo-meilus/superpipelines

Agent

Use when designing a new SKILL.md file, refining an existing skill's description for triggering, restructuring a skill into SKILL.md plus references for progressive disclosure, or extracting a skill from a workflow conversation. Does NOT design subagents (pipeline-architect) or audit existing skills (pipeline-auditor).

gustavo-meilus/superpipelines

Command

Audit one or all pipelines against layout, frontmatter, topology, and runtime-safety standards — produces a severity-classified report (SEV-0/1/2/3) with cited evidence.

gustavo-meilus/superpipelines

Command

Set, change, or audit model preferences for pipeline agents — interactive 6-mode workflow (global/workspace prefs, per-agent overrides, first-run wizard, catalog refresh).

gustavo-meilus/superpipelines

Command

Delete a step from an existing pipeline — select pipeline, select step, perform gap analysis, optionally rewire, audit the delta, then gate on human approval before any deletion.

gustavo-meilus/superpipelines

Command

Initiates a repository traversal to create localized PIPELINE-CONTEXT.md hierarchical context files.