riskrails

Plugin riskrails from marketplace riskrails in vanssata/claude-agentic-sdlc-module. Commands read from the repo's manifest — today.

Skills (8)

• rr-build-all

  Run a whole programme plan as one task in a repository that has .ai/ — every row of docs/sdlc/plans/<slug>.md becomes a step with its files, tests and dependencies; the ready steps go to parallel implementer subagents on the BALANCED tier, serialized where one depends on another; after the last step

• rr-build

  Do the work of one task in a repository that has .ai/ — resume it from its handoff, or plan and start it through /rr-plan when none is in flight; edit inside the task's files under the scope guard (widened in place with `start --amend`), run each step's own tests, show a bugfix's test failing before

• rr-plan

  Plan work before any edit. Given a spec (docs/sdlc/specs/<slug>.md), write the programme plan docs/sdlc/plans/<slug>.md — files that change, order of work, risks, proof per requirement, rollback. Given one task, measure its weight with `state.py weight` (six axes, seven lines), take the mode it give

• rr-review

  One adversarial review of the task's change, at the tier its mode sets — BALANCED in guarded, STRONG in full, security-focused when the domain axis is 2, and in light only when close reports a red fact. A fresh ai-reviewer reads the diff with bounded inputs, returns FINDINGS and a VERDICT, and state

• rr-setup

  Set up and maintain the .ai/ layer of an existing production codebase. With no flag, scaffold docs/sdlc/, the runtime directory and .ai/, ask the open options (memory, runtimes, survey depth, verify command) in one dialog, survey the code into .ai/project/ (light or full), write the Verification com

• rr-ship

  Close the task — state.py close measures the two facts (a green whole-suite verify on the tree as it is now; every changed file inside the task's files), applies the mode table and either archives the task or, in full mode, requests the human's approval and prints the exact approve command for their

• rr-spec

  Turn a rough idea into one file, docs/sdlc/specs/<slug>.md — an `## Intent` section (problem, outcome, affected users and systems, constraints, decisions taken) from a short one-question-at-a-time brainstorm recorded through state.py, then requirements and design from the architect agent on the STRO

• rr-status

  Show where the task in this directory stands, in at most twenty lines — which .ai/ root governs it, task and goal, mode and weight, stage and next action, steps and files, verify runs against the budget, the two facts, review, the approval gate, pending questions, the project's schema against the pl

Hooks (13)

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/cap-large-read.py"

• PreToolUse

  python3 -I -S "${CLAUDE_PLUGIN_ROOT}/hooks/ai-guard.py"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/runtime-gate.py"

• Setup

  "${CLAUDE_PLUGIN_ROOT}/hooks/project-scaffold.sh"

• UserPromptSubmit

  "${CLAUDE_PLUGIN_ROOT}/hooks/context-guard.py"

• PreCompact

  "${CLAUDE_PLUGIN_ROOT}/hooks/context-guard.py"

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/hooks/context-guard.py"

• Notification

  "${CLAUDE_PLUGIN_ROOT}/hooks/context-guard.py"

• PostToolUse

  python3 -I -S "${CLAUDE_PLUGIN_ROOT}/hooks/dialog-gate.py"

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/runtime-gate.py"

• SubagentStart

  "${CLAUDE_PLUGIN_ROOT}/hooks/runtime-gate.py"

• SubagentStop

  "${CLAUDE_PLUGIN_ROOT}/hooks/runtime-gate.py"

• Stop

  python3 -I -S "${CLAUDE_PLUGIN_ROOT}/hooks/dialog-gate.py"

Similar plugins