Skills

Priority Board Triage

The Priority Board's three-layer score model (rules BASE, REVIEW by the built-in AI or...

Install

npx skills add samugit83/redamon --skill priority-board-triage -g -a claude-code -y
Repository
samugit83/redamon3.3k
Category
AI and agents
Updated
3d ago
License
MIT
Context cost
Mediumabout 1,765 tokens
Runs scripts
No, instructions only

What it does

The Priority Board's three-layer score model (rules BASE, REVIEW by the built-in AI or an MCP agent, a person's DECISION) and who may write which layer. A writer that sets a final score itself, or touches another layer, silently undoes a review or a person's verdict at the next run. Trigger: editing agentic/cypherfix_triage/ (score_model, layers, evidence, orchestrator, finding_ops, prompts/review.py); editing triage_mixin.py; editing webapp/src/lib/triage/, the /api/triage routes, the Triage board components, or the MCP triage tools (triageTools.ts, verdictTools.ts).

When to Use

  • Changing the risk model, the evidence bundle, the review prompt or its validation.
  • Adding a writer of any triage_* property: a run step, a route, an MCP tool, a migration.
  • Adding a reader of the board state: a report, an MCP tool, a filter, a UI chip.

For the Cypher itself, also follow graph-db-writes; for a new MCP tool, mcp-server-tools.


Critical Rules

  • NOBODY writes a final score. triage_priority_score, triage_tier, triage_tier_rule, triage_risk, triage_factors, triage_state, triage_decided_by, triage_disposition and triage_blocker (the mixin's _FINAL_SET) come ONLY from score_model.combine_layers(), reached through layers.combine_props(). A writer changes ITS layer and asks combine for the final inside the same transaction. Setting a final directly is how a review or a verdict used to vanish at the next run.

  • Each writer touches one layer.

    WriterLayerMethod
    a run's publishBASE (+ a builtin REVIEW it made)publish_triage_layers
    an MCP agent's reviewREVIEW, channel mcpwrite_review
    a person (app, or MCP with channel mcp)DECISIONset_human_verdict
Read the whole SKILL.md on GitHub

More in AI and agents