fightingforsidewalk
- 5 skills
- 0 followers
- 12 hours ago last updated
- ▌ Chat Relay · fightingforsidewalk bundleA file-based mailbox protocol for passing messages between several Claude chats (or any AI assistants) that share one folder of Markdown files — read-and-clear as one motion, receipts, standing notes, fold-forward, and the passenger rule. Use it at the start of every turn in a multi-chat project ("check the relay", "there's a message for you from Build"), when scaffolding a new project's RELAY folder, or before sending or overwriting your own outbox file.
- ▌ Multi Chat Operating Model · fightingforsidewalk bundleThe operating model for running one project across several specialised Claude chats — named roles with one writer per file, a handoff contract, gate-by-risk, documentation by enumeration, batched writes, and the "Needs you" rule that keeps the human's asks from being buried. Use it when setting up a multi-chat project, writing or revising a project's instructions file, deciding which chat owns a document, or whenever a chat is about to produce another chat's artifact.
- ▌ Canonical Tracker · fightingforsidewalk bundleKeep one canonical Markdown tracker as the record of a project and every derived glance surface (dashboard, status page, plan document) provably in agreement with it — batched syncs, script-only edits with exact-match asserts, glyph truth, honest denominators, a closed index, an append-only archive, and a mechanical sync check that grows with every stale surface it missed. Use it when a chat maintains a project tracker or status dashboard, when closing or opening a tracked item, when figures move, or when someone asks "are you sure the numbers are right?"
- ▌ Ship Check · fightingforsidewalkPre-ship checklist for any script, tool, or repo the agent writes or packages, run before code leaves the session and before the handback is written: path traversal, command injection, secrets and names, placeholders, .gitignore, license, atomic writes, and proof that every guard has been seen to fail. Use it whenever a session is about to hand back a change that ships executable code, and name the sections that did not apply.
- ▌ Coding Agent Discipline · fightingforsidewalkHow a planning chat works with a coding agent (Claude Code or similar) so the human never has to evaluate code — writing a task as a "box" with a key-or-no-key line, scope as actions, docs by filename, observable acceptance criteria and hard stops; installing the CLAUDE.md standing behaviours and handback contract in a repo; and reading the handback that comes back as a plain-English checklist. Use it when writing a task for a coding agent, when a session's output comes back for review, or when setting up a new repo's CLAUDE.md.