AI development system — skills, agents, and hooks for systematic software engineering with Claude Code
Apply pending errata from doc 24 through the layer hierarchy: dimension, reflection, roadmap — with gate checks between layers
Run the full spec repo correction cycle: apply errata, re-evaluate reflections, deepen synthesis, and check doc hygiene
Cross-check reflection docs against dimension docs to find gaps, contradictions, and missed findings
Commit accumulated spec doc changes: survey, group by logical batch, branch, commit, merge
Severity scoring guide with few-shot examples and hard thresholds for the challenger agent.
Archive project patterns and knowledge when retiring. Categorize as transferable, historical, or deletable. Use when retiring a project or archiving knowledge. Not for: active project work, pattern recall, daily operations.
Adversarially review a plan, architecture decision, or approach. Stress-test before commitment. Use when a significant decision is being made or a plan is being finalized. Not for: data collection, project diagnostics, session debrief.
Scan client project structure, detect tech stack, check brana alignment. Use when entering an unfamiliar client project or for project health checks. Not for: business stage classification, knowledge recall, web research.
Daily venture focus card — health snapshot, pending actions, experiments. Use at session start on a venture project. Not for: deep metrics analysis, pipeline management, project alignment checks.
Find and install skills for project tech gaps. Use when entering a project with unfamiliar tech or when no local skill matches a task context.
Actively align a project with brana practices — assess gaps, plan fixes, implement structure, verify. Works for code and venture clients. Auto-detects type. Use when setting up a new project or realigning an existing one.
Security scan — secrets in CLAUDE.md, hook permissions, MCP count, dangerous settings, unencrypted .env. 5 checks, fast, zero dependencies. Run periodically or before sharing config.
Manage the backlog — plan, track, navigate phases and streams. Use when planning phases, viewing roadmaps, or restructuring work.
Interactive idea maturation — explore, research, shape raw ideas into actionable plans. Use when you have a rough idea and want to think it through.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
A Claude Code plugin that turns it into a systematic development partner -- skills, rules, hooks, and agents so Claude learns from every session, follows engineering discipline, and works consistently across all your projects.
/plugin marketplace add martineserios/thebrana
/plugin install brana
git clone https://github.com/martineserios/thebrana.git
cd thebrana && ./bootstrap.sh
/brana:build "add user authentication" -- auto-detects strategy (feature, bug fix, refactor...)
/brana:backlog start t-015 -- pick a task and enter the build loop
/brana:close -- end session, capture learnings
/brana:build detects what you're doing -- feature, bug fix, refactor, spike, migration, investigation, or greenfield -- and runs the right workflow. TDD enforced, docs included.
Hooks capture corrections, test writes, and failure cascades. /brana:close extracts patterns. Next session, they're recalled automatically. Confidence-weighted: new learnings start quarantined, proven ones surface first.
/brana:challenge runs an Opus-powered adversarial review with four flavors: pre-mortem, simplicity challenge, assumption buster, adversarial user. Auto-triggers after plan mode.
/brana:review (weekly/monthly health checks), /brana:pipeline (deal tracking), /brana:financial-model (projections + scenarios), /brana:venture-phase (milestone execution), /brana:proposal (client proposals in Spanish).
The PreToolUse hook blocks implementation writes on feat/* branches until a spec or test exists. Projects opt in by having a docs/decisions/ directory.
| Group | Skills |
|---|---|
| Core | backlog, reconcile, acquire-skills, plugin |
| Execution | build, onboard, align, client-retire |
| Learning | challenge, research, memory, retrospective |
| Venture | review, venture-phase, pipeline, financial-model, proposal |
| Session | close |
| Capture | log |
| Tools | notebooklm-source |
| Utility | scheduler, export-pdf, gsheets, respondio-prompts, meta-template |
All skills are invoked as /brana:<name>. See Skill Reference for full details.
| Agent | Model | Auto-fires when |
|---|---|---|
| memory-curator | Haiku | Starting work, familiar problem, stuck |
| client-scanner | Haiku | New client, project health check |
| venture-scanner | Haiku | New business project |
| challenger | Opus | Plan or architecture decision forming |
| debrief-analyst | Opus | End of implementation session |
| scout | Haiku | Research tasks (spawned by skills) |
| archiver | Haiku | Retiring a client |
| daily-ops | Haiku | Session start on venture project |
| metrics-collector | Haiku | Business reviews |
| pipeline-tracker | Haiku | Pipeline tracking, deal events |
| pr-reviewer | Sonnet | PR creation (auto-triggered) |
All agents are read-only. See Agent Reference for full details.
npx claudepluginhub martineserios/thebrana --plugin branaAutonomous development methodology: PRD interviews → agent execution → automated review
Structured project planning and execution through brainstorm, spec, and build phases across three execution tiers: sequential, delegated sub-agents, and full agent teams
Spec-driven development for Claude Code — requirements, plans, and tasks that ship as working code.
Plan and autonomously build a software task end-to-end. Recons the codebase, applies preloaded memory, decomposes into the right number of phases, gets one confirmation, then prepares a single ready-to-paste /goal command — one paste between you and done — that drives execution to completion with built-in retry, fix-spec recovery, and per-phase memory writeback. Works on Claude Code and Codex.
AI-powered development tools for code review, research, design, and workflow automation.
A curated set of skills for each stage of development — propose, spec, design, plan, implement, ship.