feat(opencode): add OpenUltraSAST steering skills

.opencode/skills/openultrasast-fix-audit/SKILL.md

@@ -0,0 +1,26 @@
+---
+name: openultrasast-fix-audit
+description: OpenUltraSAST patch, fix audit, differential review, adversarial review, and patch validation workflow. Use when proposing or auditing fixes for OpenUltraSAST findings from opencode.
+---
+
+# OpenUltraSAST Fix Audit
+
+Use this skill to steer fixes for OpenUltraSAST findings.
+
+## Fix Lifecycle
+
+1. Intake: restate the finding ID, evidence level, affected path, and acceptance criteria.
+2. Plan: choose the smallest defensive change that addresses the root cause.
+3. Implement: modify only files required by the finding.
+4. Adversarial review: look for bypasses, regressions, false assumptions, and unrelated edits.
+5. Reconcile: either fix the review finding or document why it is not applicable.
+6. Verify: rerun the reproducer or affected checks.
+7. Ready: only then consider advancing to `patch_validated`.
+
+## Guardrails
+
+- Do not rewrite modules when a local fix is enough.
+- Do not change public APIs unless the vulnerability requires it.
+- Do not mark a patch validated from model reasoning alone.
+- Use differential review for risky changes in auth, crypto, config, parsers, and sandbox behavior.
+- Run Semgrep or CodeQL delta checks when those analyzers supplied the original evidence.

.opencode/skills/openultrasast-kiro-impl/SKILL.md

@@ -0,0 +1,26 @@
+---
+name: openultrasast-kiro-impl
+description: OpenUltraSAST Kiro implementation steering. Use when continuing `.kiro/specs/openrouter-sast-harness/tasks.md`, choosing the next phase, updating checkboxes, or keeping implementation aligned with the spec.
+---
+
+# OpenUltraSAST Kiro Implementation
+
+Use this skill when implementing the OpenUltraSAST Kiro spec from opencode.
+
+## Rules
+
+1. Read `.kiro/specs/openrouter-sast-harness/tasks.md` before choosing work.
+2. Implement the next unchecked task slice unless the user names a different phase.
+3. Keep each slice independently verifiable with `uv run pytest`.
+4. Update task checkboxes only after implementation and tests pass.
+5. Prefer minimal harness-compatible primitives over large framework imports.
+6. Keep OpenUltraSAST independent of Clearwing; use Clearwing only as an oracle for design patterns.
+7. Use project-local opencode skills to steer scan, triage, and fix workflows.
+
+## Current Phase Order
+
+- Phase 5: Harness runtime events, processors, contracts, and traces.
+- Phase 5A: Static mapping disciplines for SARIF, Semgrep, CodeQL, differential review, and sharp edges.
+- Phase 6: Evidence ladder verifier.
+- Phase 7 and 7A: Docker sandbox and dynamic evidence.
+- Phase 8 and later: Hunter pool, SARIF, deep mode, patch oracle, MCP, fusion, skill index, hardening.

.opencode/skills/openultrasast-scan/SKILL.md

@@ -0,0 +1,35 @@
+---
+name: openultrasast-scan
+description: OpenUltraSAST scan, index, quick, standard, deep, SARIF, and report workflows. Use when running or planning `ousast scan`, repository indexing, or evidence-gated SAST analysis from opencode.
+---
+
+# OpenUltraSAST Scan
+
+Use this skill to steer OpenUltraSAST scan workflows from opencode.
+
+## Workflow
+
+1. Confirm the target is a local repository path.
+2. Run commands through uv, never by activating a virtualenv manually.
+3. Start with quick mode unless the task explicitly requires standard or deep analysis.
+4. Treat quick findings as `static_corroboration`, not verified vulnerabilities.
+5. Preserve run artifacts under `.openultrasast/runs/<scan-id>/`.
+6. Report `scan_id`, `run_dir`, finding count, and the strongest available evidence level.
+
+## Commands
+
+```bash
+uv run ousast scan <repo> --mode quick
+uv run ousast index <repo>
+uv run pytest
+```
+
+## Evidence Rules
+
+- `suspicion` means a model or weak signal raised a hypothesis.
+- `static_corroboration` means deterministic code evidence exists.
+- `crash_reproduced` requires an artifact-backed reproducer.
+- `root_cause_explained` requires independent verifier reasoning.
+- `patch_validated` requires rerunning relevant checks after the patch.
+
+Do not describe a finding as verified unless its evidence level meets the configured report threshold.

.opencode/skills/openultrasast-triage/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: openultrasast-triage
+description: OpenUltraSAST false-positive elimination, ranking calibration, evidence ladder, verifier triage, and finding adjudication. Use when reviewing findings, reducing false positives, or deciding whether evidence is enough.
+---
+
+# OpenUltraSAST Triage
+
+Use this skill when triaging OpenUltraSAST findings from opencode.
+
+## Triage Loop
+
+1. Identify the finding, path, rule, severity, confidence, and evidence level.
+2. Separate deterministic evidence from model assumptions.
+3. Check attacker control, reachability, sanitizer behavior, duplicates, impact, and contradictory evidence.
+4. If rejected or unresolved, record the false-positive reason and scope.
+5. Prefer scoped demotion over deleting a vulnerability class globally.
+6. Feed the outcome into ranking calibration and prompt constraints.
+
+## False-Positive Reasons
+
+- `unreachable_path`
+- `missing_attacker_control`
+- `sanitizer_disproved`
+- `static_rule_mismatch`
+- `incorrect_model_assumption`
+- `duplicate`
+- `insufficient_impact`
+- `unsupported`
+- `contradicted`
+- `unverified`
+
+## Decision Standard
+
+If evidence is uncertain, mark the finding as requiring next evidence instead of escalating severity. Difficult or high-impact disagreements should trigger fusion/deeper reasoning when available.