sentrux-boundaries

Étoiles13

Forks0

Mis à jour2 août 2026 à 20:35

Check `.sentrux/rules.toml` for layer and boundary violations and suggest fixes. Use when the user asks "does this respect the architecture?", "any rule violations?", "check boundaries", or "are we following the layering?". Reads the `reason` field on each violation to tailor the fix suggestion.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Source

mattapperson

mattapperson/noetic

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

SKILL.md

readonly

name	sentrux-boundaries
description	Check `.sentrux/rules.toml` for layer and boundary violations and suggest fixes. Use when the user asks "does this respect the architecture?", "any rule violations?", "check boundaries", or "are we following the layering?". Reads the `reason` field on each violation to tailor the fix suggestion.

Sentrux Boundaries

Validates architectural rules defined in .sentrux/rules.toml via the plugin:sentrux:sentrux MCP server.

Steps

Call mcp__plugin_sentrux_sentrux__scan on the repo root if the index isn't fresh.
Call mcp__plugin_sentrux_sentrux__check_rules.
For each violation:
- Classify as [[boundaries]] violation (has a reason string from the TOML) or layer_direction drift (implicit, from the layer ordering).
- For a handful of representative violations (no more than 5, highest-signal first), read the offending file and 20 lines of context around the import statement.
- Suggest a fix:
  - Context → core interpreter/runtime (acyclicity + tree-shakability): offer to move the referenced helper inline into packages/context/src/ or duplicate a narrow utility to avoid pulling the larger module.
  - Sibling-package imports (e.g. eval → code-agent): offer to move the shared code into @noetic-tools/core or refactor the caller to not need it.
  - Layer_direction drift within cli/: offer to invert the dependency (e.g. extract the shared type into cli-foundations) or accept the drift and adjust specs/22-cli-architecture.md if the intent has changed.
Group the report by reason field so the user sees the architectural theme, not just file pairs.

Guidance

Do not auto-fix without asking. List the suggestions and let the user pick.
If check_rules returns zero violations, say so in one line. Don't invent issues.
Cross-reference specs/00-overview.md and specs/22-cli-architecture.md when explaining why a rule exists — the spec is the primary source of intent, rules.toml just enforces it.
Boundaries with context layers must be tree-shakable in their reason are the highest-priority; flag those at the top of the report.

Plus depuis ce dépôt

même dépôt

noetic-agent-builder

mattapperson/noetic

This skill provides guidance for building AI agents with the Noetic framework. It should be used when creating, modifying, or composing agent patterns using Noetic's step primitives, context layers, tools, sub-harness (coding-agent) steps, generative UI (OpenUI), chat platform integration (chat-sdk.dev), and agent harness. Triggers include mentions of "agent", "react pattern", "context layer", "spawn", "tool", "loop", "sub-harness", "step.claudeCode", "Claude Code / Codex / opencode / pi as a step", "generative UI", "OpenUI", "openUi codec", "openUiSurface", "tool ui / render fragment", "chat-sdk", "noeticAgent", "Slack bot / Discord bot / Teams bot with Noetic", "getChannelStream", or any Noetic-specific API usage in the packages/core directory.

2026-08-0313

noetic-eval

mattapperson/noetic

This skill provides guidance for writing evaluations, scored tests, and optimizations for Noetic agents using the @noetic-tools/eval package. Use when creating .eval.ts files, defining scorers, running noetic-eval, or optimizing step compositions. Triggers include mentions of "eval", "scorer", "benchmark", "evaluate", "noetic-eval", "noetic test", "optimize prompts", "GEPA", "baseline", "regression", or any @noetic-tools/eval API usage.

2026-07-1513

openrouter-models

mattapperson/noetic

Query OpenRouter for available AI models, pricing, capabilities, throughput, and provider performance. Use when the user asks about available OpenRouter models, model pricing, model context lengths, model capabilities, provider latency or uptime, throughput limits, supported parameters, wants to search/filter/compare models, or find the fastest provider for a model.

2026-05-0513

sentrux-audit

mattapperson/noetic

Run a full structural audit of the noetic repo via the sentrux MCP server. Use when the user asks "how is the codebase?", "audit the repo", "full sentrux check", or after a large refactor/merge. Returns a quality score, health breakdown, rule violations, and the top untested risky files.

2026-05-0513

sentrux-baseline

mattapperson/noetic

Snapshot current sentrux metrics as a baseline so later changes can be diffed against it. Use when the user says "mark a baseline", "checkpoint quality here", "I'm about to refactor — save where we are". Pair with `sentrux-diff` after the work.

2026-05-0513

sentrux-diff

mattapperson/noetic

Compare current sentrux metrics against the most recent baseline and report what got better or worse. Use when the user asks "did I break anything?", "diff quality since baseline", "what got worse?", or at the end of a refactor. Requires a prior `sentrux-baseline` or `session_start` call in the same MCP session.

2026-05-0513

name	sentrux-boundaries
description	Check `.sentrux/rules.toml` for layer and boundary violations and suggest fixes. Use when the user asks "does this respect the architecture?", "any rule violations?", "check boundaries", or "are we following the layering?". Reads the `reason` field on each violation to tailor the fix suggestion.

Sentrux Boundaries

Validates architectural rules defined in .sentrux/rules.toml via the plugin:sentrux:sentrux MCP server.

Steps

Call mcp__plugin_sentrux_sentrux__scan on the repo root if the index isn't fresh.
Call mcp__plugin_sentrux_sentrux__check_rules.
For each violation:
- Classify as [[boundaries]] violation (has a reason string from the TOML) or layer_direction drift (implicit, from the layer ordering).
- For a handful of representative violations (no more than 5, highest-signal first), read the offending file and 20 lines of context around the import statement.
- Suggest a fix:
  - Context → core interpreter/runtime (acyclicity + tree-shakability): offer to move the referenced helper inline into packages/context/src/ or duplicate a narrow utility to avoid pulling the larger module.
  - Sibling-package imports (e.g. eval → code-agent): offer to move the shared code into @noetic-tools/core or refactor the caller to not need it.
  - Layer_direction drift within cli/: offer to invert the dependency (e.g. extract the shared type into cli-foundations) or accept the drift and adjust specs/22-cli-architecture.md if the intent has changed.
Group the report by reason field so the user sees the architectural theme, not just file pairs.

Guidance

Do not auto-fix without asking. List the suggestions and let the user pick.
If check_rules returns zero violations, say so in one line. Don't invent issues.
Cross-reference specs/00-overview.md and specs/22-cli-architecture.md when explaining why a rule exists — the spec is the primary source of intent, rules.toml just enforces it.
Boundaries with context layers must be tree-shakable in their reason are the highest-priority; flag those at the top of the report.