constraint-conflict-scanlisted
Install: claude install-skill JeelVankhede/agentsmyth
# Constraint Conflict Scan
## Purpose
Cross-check the request against `workflow/config/domain.yaml`'s configured constraints (`product`,
`safety`, `provider_neutrality`) and `repo-profile.yaml`'s protected paths, surfacing any conflict
before Think finishes framing. Prevents a brief from being written that silently violates a
constraint the repo already declared.
This is a power skill, not a lifecycle phase. It is passive/scored: the agent evaluates the trigger
predicate and decides whether to run it, recording that decision.
## Invocation Context
Use this skill when the recorded `skill_scoring` trigger for `constraint-conflict-scan` evaluates
true: `task_class != trivial OR touches_protected`.
Do not invoke it for Trivial work that touches no protected path — the check is cheap but not free,
and a Trivial change with no protected-path signal has essentially no conflict surface.
## What To Load
**Foundation** (confirm in context; load if not already present):
- Root `AGENTS.md`
- `workflow/router.md`
- `workflow/lifecycle.md`
- `workflow/rules.md`
**Minimum for invocation**:
- This file
- `references/output-schema.md`
**Before starting work**:
- `references/constraint-id-convention.md` — how constraint IDs are written in `domain.yaml` and how to cite one
- `workflow/config/domain.yaml` — the actual configured constraints
- `workflow/config/repo-profile.yaml` — `paths.protected`
## Inputs
- The request or in-progress brief draft.
- `domain.yaml`'s `constraints.{pro