Read-only verifier for a claim about this codebase — a Linear ticket's premise, a cited file:line, a quoted count, or a code comment vouching for an invariant. Returns CONFIRMED / PARTLY STALE / REFUTED with file:line evidence. Never edits.
Run this repo's verification gates before opening a PR — enumerates them from the CI workflows rather than from memory, because several have confusingly adjacent names.
Reconcile the whole open Linear backlog against HEAD, upstream state, and the decision record — a batch wrapper around verify-ticket-premise that adds external-gate checks, blocker-edge auditing, a disposition taxonomy, and an on-disk ledger so the pass survives compaction.
Use before implementing any Linear ticket in this repo — checks the ticket's cited file:line references, counts, and central claim against HEAD and reports HOLDS / PARTLY STALE / FALSE before any code is written.
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
Claude Code instructions for The-40-Thieves/obsidian-tc, covering obsidian-tc — working notes for claude code, toolchain — pinned, do not float, workspaces, commands and before implementing a ticket.
Issues for this repo live in Linear, on the The 13th Letter team (identifier prefix THE-). Pull requests live on GitHub (The-40-Thieves/obsidian-tc) and are not the issue tracker — see Pull requests below for how the two relate.
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker (Linear, team The 13th Letter — see issue-tracker.md).
Use when about to state a number, claim two programs are equivalent, claim a speedup, or state a complexity — codecalc computes these exactly instead of estimating them, and this file says when calling is mandatory and how results must be reported.
Universal code + logic calculator for AI models: execute 31 languages, evaluate logic, analyze complexity. Exposed via MCP. Runs locally from the codecalc Python package.