trails

Trails framework co-architect & CTO persona — constitutional hierarchy, drift guard, vocabulary enforcement, and architectural judgment. Use when evaluating Trails architecture, enforcing vocabulary, reviewing framework coherence, or when Clark's judgment is needed on a Trails question.

Trails framework co-architect & CTO persona — constitutional hierarchy, drift guard, vocabulary enforcement, and architectural judgment. Use when evaluating Trails architecture, enforcing vocabulary, reviewing framework coherence, or when Clark's judgment is needed on a Trails question.

Build with the Trails framework — define trail contracts, open CLI/MCP surfaces, test with examples, debug errors, migrate codebases, run governance. Use when creating trails, adding surfaces, testing, debugging Trails errors, migrating to Trails, running warden, or any work involving @ontrails/* packages.

Author, update, and manage Trails ADRs. Use when creating new ADRs, promoting drafts to accepted, updating the ADR index, renaming or renumbering ADRs, or when the user mentions ADR, architecture decision, or decision record.

Complete Trails editorial review workflow. Use when reviewing docs, ADRs, README changes, release notes, agent guidance, or docs-heavy PRs for voice, style, structure, correctness, and readiness.

Trails documentation structure and maintenance guidance. Use when creating or reorganizing Trails docs, READMEs, guides, reference pages, release docs, or agent-facing documentation.

Trails prose craft and lexicon style. Use when writing or reviewing docs, ADRs, examples, release notes, agent prompts, comments, PR descriptions, or issue language for rhythm, clarity, and vocabulary precision.

Trails writing voice and values. Use when drafting or reviewing Trails docs, ADRs, README content, release notes, agent guidance, or public explanations for stance, audience, and tone.

Author, update, and manage Trails ADRs. Use when creating new ADRs, promoting drafts to accepted, updating the ADR index, renaming or renumbering ADRs, or when the user mentions ADR, architecture decision, or decision record.

Complete Trails editorial review workflow. Use when reviewing docs, ADRs, README changes, release notes, agent guidance, or docs-heavy PRs for voice, style, structure, correctness, and readiness.

Trails documentation structure and maintenance guidance. Use when creating or reorganizing Trails docs, READMEs, guides, reference pages, release docs, or agent-facing documentation.

Trails prose craft and lexicon style. Use when writing or reviewing docs, ADRs, examples, release notes, agent prompts, comments, PR descriptions, or issue language for rhythm, clarity, and vocabulary precision.

Trails writing voice and values. Use when drafting or reviewing Trails docs, ADRs, README content, release notes, agent guidance, or public explanations for stance, audience, and tone.

Complete Trails editorial review workflow. Use when reviewing docs, ADRs, README changes, release notes, agent guidance, or docs-heavy PRs for voice, style, structure, correctness, and readiness.

Compatibility pointer for older Trails prompts. Prefer `trails-writing-voice`, `trails-writing-style`, `trails-writing-docs`, or `trails-editorial` when writing or reviewing Trails docs, ADRs, agent prompts, examples, comments, or contributor guidance.

Use when reviewing Trails-owned framework code for Result-shaped failures, resource and cwd boundaries, app loading, and documented host construction exceptions.

Autonomous codebase health scan for vocabulary drift, naming convention violations, structural anti-patterns, documentation staleness, and test health. Produces prioritized findings as Linear issues. Use for health checks, scheduled scans, or after heavy unreviewed agent work.

Autonomous codebase health scan for vocabulary drift, naming convention violations, structural anti-patterns, documentation staleness, and test health. Produces prioritized findings as Linear issues. Use for health checks, scheduled scans, or after heavy unreviewed agent work.

Dispatch the Codex custom subagent `clark` for Trails architectural decisions, vocabulary enforcement, sprint reviews, tenet checks, or any request to "ask Clark", "consult Clark", "let Clark decide", or get a CTO ruling.

Authoritative architectural ruling on a specific Trails framework question — naming choices, vocabulary compliance, pattern fitness, scope decisions. Consults the constitutional hierarchy, decides, and logs. Use when a definitive call is needed or when 'let Clark decide' is the instruction.

Big-picture architectural planning and exploration for the Trails framework. Socratic, principle-anchored exploration of features, ADRs, tenets, and horizon planning. Use when planning new capabilities, drafting or revising ADRs, exploring architectural questions, reviewing tenets, or doing horizon planning.

Trails framework design tenets — the foundational beliefs, promises, primitives, and patterns that govern the framework. Use when evaluating architectural decisions, reviewing feature proposals, checking alignment with framework principles, or when tenets, principles, or design philosophy are mentioned.

Authoritative architectural ruling on a specific Trails framework question — naming choices, vocabulary compliance, pattern fitness, scope decisions. Consults the constitutional hierarchy, decides, and logs. Use when a definitive call is needed or when 'let Clark decide' is the instruction.

Big-picture architectural planning and exploration for the Trails framework. Socratic, principle-anchored exploration of features, ADRs, tenets, and horizon planning. Use when planning new capabilities, drafting or revising ADRs, exploring architectural questions, reviewing tenets, or doing horizon planning.

Use when reviewing Trails error taxonomy, surface error projection, redaction, retryability, or Result-vs-throw boundaries. Helps distinguish runtime failures from intentional construction and host-boundary throws.

Use when a Trails change derives framework facts, projections, rule data, or surface metadata. Helps agents find authoritative owner exports and avoid shadow registries, duplicated maps, and canonical-source indirection.

Use when deciding whether a Trails hardening finding belongs in Warden, repo-local Oxlint, docs, an advisory skill, or no rule. Helps agents classify prevention candidates by owner source, Warden tier, lifecycle, diagnostic shape, and false-positive risk.

Use when comparing maturity across Trails primitives without assuming every primitive must match trail capabilities. Helps agents identify deliberate gaps, real user-facing gaps, and future-facing symmetry pressure.

Use when reviewing public or queryable Trails outputs that expose union-like shapes to agents or surfaces. Helps decide whether stable discriminants are required and whether the issue is schema cleanup, advisory guidance, or Warden work.

Trails framework design tenets — the foundational beliefs, promises, primitives, and patterns that govern the framework. Use when evaluating architectural decisions, reviewing feature proposals, checking alignment with framework principles, or when tenets, principles, or design philosophy are mentioned.