ancoder-skill-cli 0.9.1 → 0.10.0

package/README.md

@@ -252,6 +252,67 @@ If you already have OMC installed via the Claude Code plugin marketplace, the sk
 
 The embedded OMC version is pinned to the release tagged in `embedded/omc/VERSION`. To bump it, re-run the sync workflow that downloads a fresh GitHub release tarball into `embedded/omc/` and rebuild.
 
+## Meta-Harness (experimental)
+
+`meta-harness/` is a Python sub-project that implements the outer-loop harness
+optimizer from [arXiv:2603.28052](https://arxiv.org/abs/2603.28052) (Stanford, 2026).
+
+### Architecture
+
+```
+meta-harness search   ←  outer loop (Python, Claude Code proposer)
+      │
+      └─ skill-cli eval validate / run / ls / diff   ←  evaluator backend (Go)
+                │
+                └─ harness.py (user-supplied Python)  ←  inner execution layer
+```
+
+**Two independent binaries — intentionally decoupled:**
+- `skill-cli` knows nothing about `meta-harness`; it only runs harness candidates and emits scores/traces.
+- `meta-harness` knows nothing about OMC internals; it calls `skill-cli` via CLI contract only.
+
+### Quick start
+
+```bash
+# Build skill-cli
+go build -o bin/skill-cli .
+
+# Install meta-harness
+cd meta-harness
+python3 -m venv .venv && source .venv/bin/activate
+pip install -e ".[dev]"
+
+# Run smoke test (no API key needed)
+cd ..
+bash scripts/meta-harness-smoke.sh
+
+# Real search (requires ANTHROPIC_API_KEY + claude CLI)
+meta-harness search \
+  --suite meta-harness/domains/text_classification/suite.yaml \
+  --out search-runs/run-01 \
+  --max-iter 5 \
+  --k 2 \
+  --seed meta-harness/domains/text_classification/seeds/zero_shot.py \
+  --seed meta-harness/domains/text_classification/seeds/few_shot.py \
+  --skill-cli bin/skill-cli \
+  --samples 20
+```
+
+### CLI contract (skill-cli eval)
+
+| Command | Description |
+|---|---|
+| `skill-cli eval validate <dir>` | Cheap structural check (exit 0 = valid) |
+| `skill-cli eval run <dir> --suite <f> --out <d>` | Full eval → scores.json + traces/ |
+| `skill-cli eval ls --store <d> [--pareto]` | List / filter candidates |
+| `skill-cli eval diff <a> <b> --store <d>` | Code + score diff |
+
+### Tuning
+
+The `meta-harness/src/meta_harness/skill.md` file is the most important lever on search quality.
+Per Appendix D of the paper: run 3–5 short iterations (`--max-iter 3`) specifically to
+debug and refine it before committing to a full run.
+
 ## License
 
 MIT

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ancoder-skill-cli",
-  "version": "0.9.1",
+  "version": "0.10.0",
   "description": "CLI for managing everything-claude-code (ECC) components — agents, skills, commands, rules, hooks, MCP configs. Single binary, all assets embedded.",
   "bin": {
     "skill-cli": "bin/skill-cli.js"