Agent
Severity scoring guide with few-shot examples and hard thresholds for the challenger agent.
Agent
Severity scoring guide with few-shot examples and hard thresholds for the challenger agent.
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.
Agent
Grade completed implementation against task acceptance criteria. Use at close step after a build. Not for: plan review, code quality, style, PR gating.
Agent
Adversarially review a plan, architecture decision, or approach. Stress-test before commitment. Use when a significant decision is being made. Not for: data collection, project diagnostics.
Agent
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.
Agent
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.
Agent
Extract errata, learnings, and patterns from a work session. Use at end of implementation sessions or when notable learnings emerge. Not for: adversarial review, project scanning, knowledge recall.
Agent
Delegate to agy (Gemini Flash). Use for research, boilerplate, doc drafts, batch summarization. Not for: knowledge recall, project diagnostics.
Agent
Recall patterns from knowledge system, cross-pollinate across clients, check knowledge health. Use when starting work on a topic or periodic checks. Not for: codebase search, project scanning.
Agent
Collect venture metrics from snapshots, experiments, pipeline, financials. Use when /brana:review runs (weekly, monthly, or check). Not for: daily focus cards, deal-level analysis, general research.
Agent
Pipeline status — deal stages, overdue follow-ups, conversion trends. Use when pipeline or deal-related work is happening. Not for: broad metrics aggregation, daily priorities, venture diagnostics.
Agent
Review PR diffs for code quality, bugs, and style issues. Auto-triggered on PR creation. Not for: implementation, file editing, test writing.
Agent
Fast research for codebase exploration and web search. Use when finding files, searching code, or fetching external info. Not for: knowledge recall, project diagnostics, business analysis.
Agent
Diagnose a business project — classify stage, recommend frameworks, identify gaps. Use when first encountering a business project or for health audits. Not for: tech stack assessment, daily operations, metrics collection.
Command
Task: t-1341 Related: docs/architecture/testing-validation.md (canonical enum source).
Command
Task: t-1343 Related: tasks.spec.md (rotation contract).
Command
Task: t-1355 Command: brana backlog triage-stale.
Command
Commit accumulated spec doc changes: survey, group by logical batch, branch, commit, merge.
Hook
Runs before the agent uses a tool for Write, Edit, Write, Edit, Write, Edit, Write, Edit, Write, Edit, EnterPlanMode, Bash, Bash, Bash, Bash, Bash, Bash, Bash, Bash, Bash, Bash, Bash, mcp__brana__backlog_ac_approve, mcp__brana__backlog_wave_approve, mcp__brana__backlog_wave_set and Bash tool calls, executing…
Hook
Runs after a tool call finishes for Skill, ExitPlanMode, Bash, Bash, Bash, Bash, Write, Edit, Write, Edit, Write, Edit, Write, Edit, Write and Edit tool calls, executing post-tool-use.sh, skill-sentinel.sh, post-plan-challenge.sh, post-pr-review.sh, task-completed.sh, hallucination-detect.sh, bash-output-compress.sh…
Hook
Runs when a tool call fails, executing post-tool-use-failure.sh via bash. From martineserios/thebrana.
Hook
Runs when you submit a prompt, before the agent sees it, executing preflight-model.sh, context-inject.sh, signal-capture.sh and presence-refresh.sh via bash (4 commands). From martineserios/thebrana.
Hook
Runs when a session starts, executing session-start.sh and cc-changelog-check.sh via bash (2 commands). From martineserios/thebrana.
Hook
Runs when a subagent starts, executing subagent-context.sh and subagent-tracker.sh via bash (2 commands). From martineserios/thebrana.