🦒 Zuraffa AI first Flutter Clean Architecture Framework and CLI
This repository also configures its own agents. See what zuraffa tells them →
Command Claude Code needs its repo
Re-evaluate since the last run: compute the git/.memsearch/TDD delta, re-score previously graded files in light of what changed, and report which past suggestions were resolved or are now stale/false.
Command Claude Code needs its repo
Bootstrap MD Doctor: write its config (if missing) and snapshot the current ground truth (git HEAD, TDD verdicts, .memsearch records) as the baseline for future drift checks.
Command Claude Code needs its repo
Render the latest (or a specific) health report: average truthfulness, counts of truthful/stale/false/obsolete docs, and the queue of update/delete/create actions.
Command Claude Code needs its repo
Deep-diagnose every tracked/untracked .md file: gather git creation+modification metadata, fact-check each doc's claims against ground truth, grade truthfulness 0-100, and write per-file suggestions (update/delete/create/keep).
Command Claude Code needs its repo
On-demand view of specs whose latest test evidence is red or unknown, with the exact evidence line quoted from tdd/cycle-log.md and the command that would produce evidence.
Command Claude Code needs its repo
On-demand view of everything not complete: what stage each is stuck at, what the immediate next artifact/command is, oldest-untouched first, stale warnings past staleafterdays.
Command Claude Code needs its repo
Main generator — scans all specs//, derives per-feature stage, task progress, health, last updated; when the TDD extension is installed, adds a deep TDD table (acceptance/unit/characterization counts, DONE, loop mode, tasks.md state); renders dashboard to configurable output path and writes .specify/stats/stats.json…
Command Claude Code needs its repo
On-demand execution — reads verified suite command from .specify/memory/tdd-profile.md, runs it for selected specs (--all, spec id/slug, or default active feature), captures pass/fail + duration + tail, appends run record to .specify/stats/runs.json, refreshes dashboard health column.
Command Claude Code
Derive the feature's test list by delegating to zfa tdd plan (deterministic engine); falls back to LLM-guided derivation only when zfa is unavailable.
Command Claude Code
Drive the red-green-refactor loop by delegating to zfa tdd run (deterministic engine); the LLM handles only honest stops — fixing genuine reds and remediation — never re-driving what zfa drives.
Command Claude Code
Detect the test stack and write .specify/memory/tdd-profile.md; zuraffa-wired projects record zfa commands as the engine.
Command Claude Code
Audit TDD discipline by delegating to zfa tdd verify (mutation testing, evidence integrity); the LLM interprets the verdict and drives remediation.
Command Claude Code
Create Zorphy entities with fields.
Command Claude Code
Regenerate all extension command files from zfa manifest.
Command Claude Code
Set up a fresh Flutter project for Zuraffa code generation.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: