241 tagged architecture, measured the same way as everything else here.
Browse within: developer-tool 36scaffolding 36sdl 36ci-cd 24code-quality 23adhd-friendly 22claude-plugin 22developer-toolkit 22codex-skill 19ai-code 17ast 17conventions 17adr 15gcp 14
Command
Individual command implementations, one file per command. Each exports an async or sync function invoked by the CLI dispatcher. Commands fall into three groups: local operations (init, list, show, delete, status, diff, refs, validate, class-field), cloud operations (login, logout, link, push, pull, share, org), and…
Command Claude Code
Run a CKB-augmented compliance audit optimized for minimal token usage.
Command Claude Code
Run a CKB-augmented code review optimized for minimal token usage.
Command Codex
Create an Architecture Decision Record.
Command Codex
Validate architecture against all GDDs.
Command
Trigger/Process/Rules sections below (Claude Code skills need self-contained instructions and can't just point at another file) — keep the two in sync. tools/claude-code/README.md links here rather than keeping its own copy. -->.
Command
Render an animated OpenHop flow diagram for the prompt that follows. Sketches the YAML, pushes it to the local OpenHop server, and returns the per-flow render URL.
Command
List every OpenHop flow currently stored on the local OpenHop server, with id, title, and per-flow URL.
Command Claude Code
Audit a README's reading flow by treating it as a conversion funnel. Every section is evaluated against a target reader and a terminal action. Produces a structured audit blueprint that feeds directly into /readme-restructure.
Command Claude Code
Execute a /readme-audit blueprint. Rewrites the README to the evaluator → conversion → links structure and creates linked docs by extracting and reorganising existing content.
Command Cursor
Generate a post-AI-edit confidence report showing what changed, what evidence was checked, what risks remain, and what to inspect at 3AM.
Command Cursor
Structured review workflow before merging changes. Produces actionable feedback with architecture grounding.
Command Cursor
Use this after an sruja agent loop, sruja agent apply, or sruja agent run --mode apply completes. This command guides your editor agent to distill lessons into agent memory.
Command Claude Code
Legacy code archaeology and context bootstrap. Reads code, git history, Jira (when configured), and remote PRs/issues to reconstruct WHY a module exists. Produces discovery notes in memory/, ADR candidates and PRD candidates in docs/ for human review, then re-indexes memory.
Command Claude Code
Implement a feature from a PRD.
Command Claude Code
Analyze recent work and extract patterns to improve skills and conventions.
Command Claude Code
Run graspanalyze + graspminimalcontext for the current repo, store the sessionid, and report a 100-token orientation.
Command Claude Code
Detect changes since base branch and produce a risk-scored impact report.
Command Claude Code
Full PR review with blast-radius, suggested questions, and surprising-connections check.
Command
Audit code, documentation, and history for potential architecture decisions that were never recorded, then return a deduplicated evidence report. Read-only.
Command
Check the current change, or a plan, against the decisions that govern it and report a verdict per decision. Read-only.
Command
Draft one new ADR from a current decision or a selected backfill handoff. Writes a single new record, as proposed.
Command
Brainstorm a feature idea through conversation until it's ready for /spec.
Command
Run a retrospective on a completed spec to capture lessons learned.