Agent
A context append names the home of record and a one-line gist; it never restates the content. If an inline append grows past a paragraph, that is the signal it is really one of these documents.
3 2d ago A 0 tokens
original MIT
3Stars on the repository
73Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Agent
Severity scoring guide with few-shot examples and hard thresholds for the challenger agent.
3 2d ago A 20 tokens
original MIT
archiver
03Agent
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.
3 2d ago A 45 tokens
original MIT
Agent
Grade completed implementation against task acceptance criteria. Use at close step after a build. Not for: plan review, code quality, style, PR gating.
3 2d ago A 34 tokens
original MIT
challenger
05Agent
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.
3 2d ago A 40 tokens
original MIT
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.
3 2d ago B 44 tokens
original MIT
daily-ops
07Agent
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.
3 2d ago B 40 tokens
original MIT
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.
3 2d ago A 46 tokens
original MIT
gemini
09Agent
Delegate to agy (Gemini Flash). Use for research, boilerplate, doc drafts, batch summarization. Not for: knowledge recall, project diagnostics.
3 2d ago A 35 tokens
original MIT
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.
3 2d ago A 42 tokens
original MIT
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.
3 2d ago B 47 tokens
original MIT
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.
3 2d ago B 40 tokens
original MIT
pr-reviewer
13Agent
Review PR diffs for code quality, bugs, and style issues. Auto-triggered on PR creation. Not for: implementation, file editing, test writing.
3 2d ago A 36 tokens
original MIT
scout
14Agent
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.
3 2d ago A 38 tokens
original MIT
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.
3 2d ago B 44 tokens
original MIT