feat: deliver v1.8.0 harness reliability and parity updates

docs/releases/1.8.0/linkedin-post.md

@@ -0,0 +1,13 @@
+# LinkedIn Draft - ECC v1.8.0
+
+ECC v1.8.0 is now focused on harness performance at the system level.
+
+This release improves:
+- hook reliability and lifecycle behavior
+- eval-driven engineering workflows
+- operator tooling for autonomous loops
+- cross-platform support for Claude Code, Cursor, OpenCode, and Codex
+
+We also shipped NanoClaw v2 with stronger session operations for real workflow usage.
+
+If your AI coding workflow feels inconsistent, start by treating the harness as a first-class engineering system.

docs/releases/1.8.0/reference-attribution.md

@@ -0,0 +1,16 @@
+# Reference Attribution and Licensing Notes
+
+ECC v1.8.0 references research and workflow inspiration from:
+
+- `plankton`
+- `ralphinho`
+- `infinite-agentic-loop`
+- `continuous-claude`
+- public profiles: [zarazhangrui](https://github.com/zarazhangrui), [humanplane](https://github.com/humanplane)
+
+## Policy
+
+1. No direct code copying from unlicensed or incompatible sources.
+2. ECC implementations are re-authored for this repository’s architecture and licensing model.
+3. Referenced material is used for ideas, patterns, and conceptual framing only unless licensing explicitly permits reuse.
+4. Any future direct reuse requires explicit license verification and source attribution in-file and in release notes.

docs/releases/1.8.0/release-notes.md

@@ -0,0 +1,19 @@
+# ECC v1.8.0 Release Notes
+
+## Positioning
+
+ECC v1.8.0 positions the project as an agent harness performance system, not just a config bundle.
+
+## Key Improvements
+
+- Stabilized hooks and lifecycle behavior.
+- Expanded eval and loop operations surface.
+- Upgraded NanoClaw for operational use.
+- Improved cross-harness parity (Claude Code, Cursor, OpenCode, Codex).
+
+## Upgrade Focus
+
+1. Validate hook profile defaults in your environment.
+2. Run `/harness-audit` to baseline your project.
+3. Use `/quality-gate` and updated eval workflows to enforce consistency.
+4. Review attribution and licensing notes for referenced ecosystems: [reference-attribution.md](./reference-attribution.md).

docs/releases/1.8.0/x-quote-eval-skills.md

@@ -0,0 +1,5 @@
+# X Quote Draft - Eval Skills Post
+
+Strong eval skills are now built deeper into ECC.
+
+v1.8.0 expands eval-harness patterns, pass@k guidance, and release-level verification loops so teams can measure reliability, not guess it.

docs/releases/1.8.0/x-quote-plankton-deslop.md

@@ -0,0 +1,5 @@
+# X Quote Draft - Plankton / De-slop Workflow
+
+The quality gate model matters.
+
+In v1.8.0 we pushed harder on write-time quality enforcement, deterministic checks, and cleaner loop recovery so agents converge faster with less noise.

docs/releases/1.8.0/x-thread.md

@@ -0,0 +1,11 @@
+# X Thread Draft - ECC v1.8.0
+
+1/ ECC v1.8.0 is live. This release is about one thing: better agent harness performance.
+
+2/ We shipped hook reliability fixes, loop operations commands, and stronger eval workflows.
+
+3/ NanoClaw v2 now supports model routing, skill hot-load, branching, search, compaction, export, and metrics.
+
+4/ If your agents are underperforming, start with `/harness-audit` and tighten quality gates.
+
+5/ Cross-harness parity remains a priority: Claude Code, Cursor, OpenCode, Codex.