claudecodex

wayfare

Plan work and have agents execute it, in a repo and across a fleet of them

5 on GitHubby AI Hero Incv2.1.0MITupdated yesterdayDeveloper Tools
/

Plugin wayfare from marketplace wayfare in ai-hero/wayfare-skills. Commands read from the repo's manifest — today.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (30)

  • security-audit

    Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full/compr

  • wayfare-advance-item

    Advance one item through its permitted gates. Handle a ready task, a Dependabot PR, or one goal turn. Do not plan. Use to advance a specific item by id.

  • wayfare-audit-compliance

    Audit this repo against the compliance baseline, or audit the fleet at merged state. Report register defects, regenerate CONSISTENCY.md, and draft template backports. Use to check compliance without a full roadmap sync.

  • wayfare-audit-deep

    Run the vendored Cloudflare security audit on one repo, with a stated budget and source-only by default. Use when a person explicitly asks for a deep security audit or a pen test of a repo, and only then. Not for a security question, a PR review, or dependency and image scanning.

  • wayfare-audit-plugin

    Audit skill quality, consistency, duplication, HERO.md field coverage, and readability in the wayfare plugin. Use before releasing plugin changes.

  • wayfare-audit-security

    Run by wayfare-sync-plan. Audit dependency CVEs, container CVEs with Scout and Trivy, and code hardening. Write executable security plans under .plans. Never edit source.

  • wayfare-build-task

    Build one small task through planning, implementation, review, and shipping, or resume the current goal. Use for a low-risk change that fits one PR. Route larger or irreversible work through wayfare-sync-plan.

  • wayfare-check-audit-claim

    Check a claim from a compliance tool against what the auditor was told and against independent evidence. Report it as a claim row. Read only. Use before reporting a test result, deadline, fix or task from a tool such as Vanta, or before filing a ticket from one, even when nobody asked for a check.

  • wayfare-check-preflight

    Check tooling, HERO.md freshness, .env keys, and ports before the pipeline changes state. Use before wayfare-push-pr, wayfare-ship-pr, or wayfare-build-task, or when a pipeline fails during setup.

  • wayfare-create-skill

    Create an Agent Skill or a supported client-specific agent, rule, or hook. Define its triggers and success criteria. Use when extending an agent client or adding a reusable workflow.

  • wayfare-drop-item

    Drop an open item with a recorded reason. For an unmerged branch, stash and switch only with a named, confirmed stash. Change no git state for an item without a branch. Use when abandoning work.

  • wayfare-grill-idea

    Brainstorm and plan through one question at a time. Write work items with dependencies. Use for vague tasks, features, refactors, or migrations beyond one small change, before an unstated assumption, or before a decision that is expensive to reverse. Skip typos, copy edits, and dependency bumps.

  • wayfare-init-repo

    Investigate a repo, write HERO.md, and create .plans/PLAN.md. Migrate an older store when found. Scaffold first in an empty directory. Use on a repo with no HERO.md or no .plans/PLAN.md.

  • wayfare-model-data

    Model stored data, write migrations, add indexes, cache reads, and fix slow queries in a MongoDB and Redis backend. Use before adding or changing a stored field, collection, store method, query, index, cached read, or boot migration. Use when an endpoint is slow or uncached, even if nobody mentions

  • wayfare-one-shot

    Draft one small task from a clear description. Show it and ask before marking it ready and building it through a merged PR. Route multiple items, anti-features, and irreversible changes to wayfare-grill-idea. Use for a fix you already understand.

  • wayfare-push-pr

    Test the work, commit it, push it, and open a draft PR with a CI report. Use when work is ready to check or share. Use test or commit mode to stop before publishing.

  • wayfare-recalibrate-config

    Report and tune HERO.md config for wayfare, including Connections, Wayfare, and the architecture and security stages. Ask only about unset or incorrect fields. Use after a config failure or a change to the repo's structure.

  • wayfare-recomponentize-ui

    Refactor UI into atomic layers, replace off-token styling, and source primitives from a configured registry or stock shadcn. Use when asked to recomponentize, refactor UI, adopt a design system, or clean up component structure.

  • wayfare-respond-pr

    Address actionable PR review comments. Check the fixes and resolve the corresponding conversations. Use when a reviewer or review bot leaves feedback on your pull request.

  • wayfare-review-architecture

    Compare DESIGN.md with the code. Report stale claims, missing layers, obsolete sections, and a missing or stale Source ref. Write nothing. Use to check the architecture record before trusting it.

  • wayfare-review-fleet

    Compare FLEET.md with sibling checkouts. Report rows not cloned here, moved or broken checkouts, and port collisions. Write nothing. Use from the folder containing the repos to check the map before a fleet run.

  • wayfare-review-pr

    Review a PR with independent quality and security passes. Apply fixes only in self-review mode. Use before marking your PR ready or when reviewing another author's PR without editing it.

  • wayfare-setup-dev

    Check local tools and credentials against HERO.md, or set up a whole machine from the fleet's .fleet/setup.yaml when run at the fleet root. Guide git config, CLI sign-ins and missing dependencies. Never change shared files. Use on a fresh machine or clone, or when a tool or login is missing.

  • wayfare-ship-pr

    Trigger the configured approval workflow and read its verdict. Merge an approved PR and check state after the merge. Use after review when a pull request is ready to ship.

  • wayfare-start-goal

    Ask the user to authorize the next goal, then run its first turn. Keep the grant in the session. Never store it. Use when the roadmap is planned and the user is ready to build the next goal.

  • wayfare-sync-architecture

    Create DESIGN.md when absent or apply drift findings from an architecture review. Write only changes the user confirms. Keep Decisions append-only. Use after wayfare-review-architecture reports findings or to create the record.

  • wayfare-sync-fleet

    Create or update FLEET.md, the fleet map of sibling checkouts, groups, and ports, kept in the register checkout at .fleet/. Propose rows and write only what the user confirms. Use from the folder containing the repos when adding a checkout or claiming a port. Use wayfare-review-fleet to report drift

  • wayfare-sync-plan

    Refresh .plans against architecture, design, hardening, stale prose, compliance, dependency PRs, unmerged work, and goals. Propose items and goals. Write only what the user confirms. Use to refresh the roadmap.

  • wayfare-write-handoff

    Write one work item with session context, decisions, remaining work, and acceptance criteria for an agent with no session context. Use when stopping during a task, transferring work, or filing session findings as a ticket.

  • write-like-me

    Write or rewrite prose so it sounds like Rahul wrote it, in plain words, AI patterns removed, for blogs, LinkedIn, book chapters, business writing, slides, docs or code comments. Use when asked to humanize, de-AI, write it like me, rewrite in my voice, draft from notes or fix titles, after an agent

Hooks (2)

  • Stop

    "${CLAUDE_PLUGIN_ROOT}/hooks/check-deferrals.sh"

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/hooks/check-floors.sh"

View source on GitHub

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Maintain wayfare?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted