claudecodex

specclaw-bf

Brownfield rebuild add-on for specclaw: analyze, clarify, baseline, replay and rebuild a legacy app.

14 on GitHubby Chandima Ranaweerav0.9.5MITupdated yesterday
/

Plugin specclaw-bf from marketplace chan4lk in chan4lk/specclaw. Commands read from the repo's manifest — yesterday.

What it installs

Skills (15)

  • bf-analyze

    Use when onboarding to an existing or legacy codebase that needs a grounded stack, dependency and risk report.

  • bf-architecture

    Use when a legacy codebase needs a C4 architecture view before a rebuild.

  • bf-baseline

    Use when a rebuild needs golden-master seams, scenarios and a capture harness from the legacy app.

  • bf-blueprint

    Use when a rebuild's decisions and backlog exist and the target architecture must be drawn.

  • bf-bootstrap

    Use when a rebuild backlog exists but the new repo has no application foundation yet.

  • bf-clarify

    Use when brownfield analysis has open inferences or gaps that need human answers.

  • bf-domain

    Use when a legacy codebase needs its domain model, functional spec and module map.

  • bf-e2e

    Use when an application needs runnable end-to-end tests that assert its own business behaviour.

  • bf-prototype

    Use when a rebuild answered SQ-013 REINTERPRET and the redesigned screens need client approval.

  • bf-quality

    Use when a legacy or rebuilt codebase needs measured complexity, duplication and size metrics.

  • bf-rebuild-plan

    Use when brownfield analysis is done and the app must become an ordered rebuild backlog.

  • bf-replay

    Use when rebuilt code must be compared against captured legacy golden-master fixtures.

  • bf-status

    Use when the user asks where a brownfield rebuild stands or which bf command is next.

  • bf-ui

    Use when a rebuild must keep the legacy UI's screens and visual theme.

  • propose

    Use when proposing a change in a brownfield rebuild repo that has a rebuild backlog.

Subagents (14)

  • bf-architecture-analyst

    Writes a grounded C4 architecture view of a legacy codebase for /specclaw-bf:bf-architecture.

  • bf-baseline-designer

    Designs golden-master seams, scenarios, harness code and the error map for /specclaw-bf:bf-baseline.

  • bf-blueprint-architect

    Draws the rebuild's target architecture from its recorded decisions for /specclaw-bf:bf-blueprint.

  • bf-bootstrap-architect

    Scaffolds the new repo's foundation for the decided stack, with no backlog capability, for /specclaw-bf:bf-bootstrap.

  • bf-clarify-extractor

    Turns analysis gaps into numbered, answerable questions and decision papers for /specclaw-bf:bf-clarify.

  • bf-codebase-analyst

    Writes a grounded codebase report for a legacy app for /specclaw-bf:bf-analyze.

  • bf-domain-analyst

    Writes the domain model, functional spec and module map for /specclaw-bf:bf-domain.

  • bf-e2e-architect

    Picks an E2E framework for the app's stack and writes page objects and tests for /specclaw-bf:bf-e2e.

  • bf-prototype-architect

    Writes the prototype brief for a REINTERPRET rebuild for /specclaw-bf:bf-prototype.

  • bf-quality-analyst

    Narrates a bash-computed quality JSON into a readable report for /specclaw-bf:bf-quality.

  • bf-rebuild-planner

    Drafts the ordered, module-grouped rebuild backlog for /specclaw-bf:bf-rebuild-plan.

  • bf-replay-auditor

    Cites the decision that sanctions each behavioural replay divergence, or says none exists.

  • bf-replay-mapper

    Maps legacy fixtures onto the rebuild's seams and writes the replay tests for /specclaw-bf:bf-replay.

  • bf-ui-analyst

    Extracts legacy screens and design tokens, and the capture checklist, for /specclaw-bf:bf-ui.

View source on GitHub chan4lk.github.io

More from chan4lk/specclaw

All 6 plugins →

specclaw-extras

claudecodex

Optional specclaw skills: auto, loop, learn, patterns, context, author-spec, debug, renumber and the review panel.

8 skills · 7 agents

14

specclaw

claudecodex

Lean, output-first spec-driven builds: mock first, then propose, plan, build, verify, pr.

8 skills · 2 agents · hooks

14

specclaw-fleet

claudecodex

Fleet add-on for specclaw: run approved changes headless in sandboxed K3s jobs with Claude or Codex on the work-item assignee's own plan, tracked in Azure Boards.

6 skills

14

specclaw-review

claudecodex

Local review loop for specclaw: layered review rules, converging rounds, a bounded review memory behind an MCP server.

3 skills · 1 MCP server · hooks

14

specclaw-sync

claudecodex

Tracker sync add-on for specclaw: GitHub issues, Azure DevOps boards and PRs, Jira.

5 skills

14

Similar plugins

code-modernization

claude

Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).

13 commands · 8 agents · hooks

anthropics/claude-plugins-official 47,076

skill-retro

claude

Grade an agent setup from real conversation history — a rebuild of warpdotdev/common-skills' skill-doctor (MIT). Harvests recent local Claude Code and Codex sessions scoped to one repo, condenses and secret-redacts transcripts (12-pattern redactor, chmod-0600 artifacts, nothing uploaded), has the agent judge each transcript against two verbatim-preserved rubrics (efficiency, code quality — labels only), then runs a deterministic aggregation gate that derives every number from the label tables, refuses scores for unsampled sessions and suggestions that cite no scored session, and renders one self-contained zero-JS HTML report (dark-mode, print-to-PDF). Proposed skill edits stay staged as diffs until an explicit per-skill yes; zero suggestions is a valid, reportable success. Ships cs-skill-retro agent, /cs-skill-retro command, 3 stdlib tools, 3 references citing 7 sources each.

1 skill · 1 command · 1 agent

alirezarezvani/claude-skills 29,725

gsd-core

claude

GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.

72 skills · 72 commands · 64 agents · hooks

open-gsd/gsd-core 11,494

designlang

claude

Thirteen slash commands wrapping the designlang CLI: /extract (full design language → DTCG, Tailwind, Figma), /site (crawl a whole site → one canonical design system + consistency grade), /grade (shareable HTML report card + SVG badge), /battle (head-to-head graded comparison), /remix (restyle in 6 vocabularies — brutalist, swiss, art-deco, cyberpunk, soft-ui, editorial), /pack (one downloadable design-system bundle), /theme-swap (OKLCH-correct recolour around a new brand primary), /brand (full editorial brand-guidelines book — 13 chapters, hand-off-ready), /pair (fuse two designs across configurable axes — colours from one site, typography from another), /studio (live token-editor with component preview + export), /verify (rebuild from tokens and pixel-diff vs live for a fidelity score), /fidelity (score a clone vs the original — visual pixel-diff + motion fidelity — with a ranked correction plan), /gallery (build a shareable static gallery of measured clones).

2 skills · 14 commands

Manavarya09/design-extract 5,068

conductor

claude

Conductor is a set of modular AI agent skills for Claude Code that enables Spec-Driven Development.

6 skills

gemini-cli-extensions/conductor 3,791

Maintain specclaw-bf?

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 plugins6 plugins