refactor(plugin)!: ship as a Claude Code plugin, one dir link per harness

Skills move to skills/<name>/SKILL.md and the repo gains both manifests, so
it is now a marketplace hosting exactly one plugin whose root is the repo
root (source: "."). Claude Code installs it from git; no symlinks involved.

Why: install.sh wired the library into every consuming repo as an ABSOLUTE
symlink to $CHECKOUT_DIR. The checkout moved three times, most recently when
local-dev@1966d5a dropped the embedded .skills/ copy, and nothing migrated
the links — 243 dangling links across 12 repos, hidden from git by the
**/.claude/skills/ ignore rule. Worse, ~/dev spans two path roots
(/Users/mathias on the iCloud-shared Macs, /home/mathias on koala), so an
absolute link stored there is broken on one side by construction. Re-running
the installer cannot fix that; only removing the mechanism can.

install.sh keeps the harnesses with no plugin system and drops from 42 links
per harness to one directory link, via the convergent ~/.agents/skills
convention that Pi and OpenCode both read:

  ~/.agents/skills          -> $CHECKOUT_DIR/skills
  ~/.config/crush/skills    -> ~/.agents/skills
  ~/.config/opencode/skills -> ~/.agents/skills

wire_claude_repo is deleted outright rather than gated behind a flag — on a
mixed-root fleet it cannot be made correct. Antigravity and Vibe targets go
too; both unused. CHECKOUT_DIR keeps its host-local default deliberately:
pointing it into ~/dev would put a git working tree inside iCloud with two
concurrent writers.

Taskfile drops five near-identical wiring loops (they had already drifted)
and delegates to install.sh. `task check` gains frontmatter validation, a
stray-root-entry gate, and manifest/tag version parity — the loose
secret-hygiene.md sat unloadable for months because nothing checked layout.

Verified: claude plugin validate . passes clean; a probe skill loaded as
skills:zzprobe through --plugin-dir; task check green at 42 skills.

Refs: #23
Bump-Type: minor

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m

skills/regulatory-risk-assessment/SKILL.md

@@ -0,0 +1,110 @@
+---
+name: regulatory-risk-assessment
+description: Produce a structured regulatory risk assessment / risk-register entry for regulated-industry features (banking, payments, PSD2/PSR, DORA, AML). Use when filing a CAD issue that needs a Risk:LOW/MEDIUM/HIGH level, or designing features touching payments, auth, data storage, or external APIs ("what are the risks?", "compliance gate", "risk register").
+---
+
+# regulatory-risk-assessment
+
+Produce a structured regulatory risk assessment for a feature, component,
+or integration — generating a risk register entry that satisfies the
+audit requirements of regulated-industry clients (banking, finance,
+insurance, PSD2/PSR, DORA, AML/KYC contexts).
+
+**Use when:**
+- Filing a Gitea issue dispatched via CAD (needs Risk: LOW/MEDIUM/HIGH)
+- Designing a feature touching payments, auth, data storage, external APIs
+- Preparing a client deliverable in a regulated industry
+- "what are the risks?" / "compliance gate" / "risk register" in session
+
+**Do not use for:** routine refactoring, docs-only changes, internal
+tooling with no external data or user impact.
+
+## What this skill produces
+
+A docs/risk-register.md section with this schema:
+
+  ### R-[DOMAIN]-[NN] — [Short risk title]
+
+  | Field | Value |
+  |-------|-------|
+  | Risk | What could go wrong (concrete, specific) |
+  | Regulatory reference | Which obligation/regulation, if any |
+  | Likelihood | H / M / L |
+  | Impact | H / M / L |
+  | Overall | H / M / L (highest of likelihood x impact) |
+  | Mitigation | What we are doing about it |
+  | Validation | Test name or Gitea issue number |
+  | Status | open / mitigated / accepted |
+
+Risk ID namespace:
+  R-AUTH-NN  authentication and authorization
+  R-DATA-NN  data storage, retention, privacy
+  R-API-NN   external API integration
+  R-PAY-NN   payment and financial transactions
+  R-INFRA-NN infrastructure and availability
+  R-AGENT-NN agentic / AI execution
+  R-COMP-NN  compliance and regulatory obligation
+
+## Mechanics
+
+Step 1 — Scope the assessment
+  1. What external systems does this touch?
+  2. What user data does it read, write, or transmit?
+  3. What happens on silent failure? Loud failure?
+  4. What is the blast radius of a worst-case bug?
+  5. Is a regulation implicated?
+
+Step 2 — Enumerate risks (common examples)
+  Auth/OAuth: token theft, refresh failure, insufficient scope
+  Email/Gmail: misclassification archives HUMAN thread, PII in logs
+  Payment/PAIN.001: wrong amount, duplicate submission, missing field
+  Agentic: irreversible action without approval, prompt injection, spirals
+  Infra: single point of failure, secret in logs
+
+Step 3 — Declare overall risk level
+  Highest individual risk = feature overall level (LOW/MEDIUM/HIGH).
+  This is the **Risk:** declaration in the CAD agent-ready issue contract.
+
+Step 4 — Write validations
+  Every mitigation needs a validation:
+    - Specific test name (TestXxx)
+    - Gitea issue number
+    - Manual verification step with acceptance criteria
+  Not acceptable: "will test later", "review manually"
+
+Step 5 — Update docs/risk-register.md
+  Append entries. Create if absent:
+
+    # Risk Register
+    All entries follow R-[DOMAIN]-[NN] schema.
+    See skills/regulatory-risk-assessment/SKILL.md for conventions.
+    Last updated: [date]
+
+## Integration with assessor-loop
+
+For complex regulated-industry features (PSD2/PSR, DORA, AML), route to
+mathias/assessor-loop for deep obligation decomposition first.
+Use this skill standalone for internal tooling or general engineering risk.
+
+## Integration with CAD
+
+Every CAD-dispatched issue must include:
+  **Risk:** LOW | MEDIUM | HIGH
+
+CAD pre-flight (agentsquad#29) rejects issues without it.
+If genuinely no risks: declare LOW and note why.
+
+## Example entry
+
+  ### R-DATA-01 — Email misclassification archives a HUMAN thread
+
+  | Field | Value |
+  |-------|-------|
+  | Risk | LLM labels a real person's email as NOISE, causing auto-archive |
+  | Regulatory reference | None (internal) |
+  | Likelihood | M |
+  | Impact | H |
+  | Overall | H |
+  | Mitigation | Phase 1 read-only; HUMAN class never auto-archived in any phase |
+  | Validation | TestClassifier_HumanThreadNeverArchived; 1-week Phase 1 review |
+  | Status | open |