diff --git a/.github/workflows/analysis.yml b/.github/workflows/analysis.yml
index ee0d384..c5415de 100644
--- a/.github/workflows/analysis.yml
+++ b/.github/workflows/analysis.yml
@@ -23,6 +23,8 @@ jobs:
           cache: pip
           cache-dependency-path: pyproject.toml
       - run: python -m pip install .
+      - run: 'python -c "from pathlib import Path; import sys; p = Path(''.agent-tools/code-guard.loc-baseline.json''); present = p.exists() or p.is_symlink(); print(''Forbidden LOC baseline present: .agent-tools/code-guard.loc-baseline.json'', file=sys.stderr) if present else None; raise SystemExit(1 if present else 0)"'
+      - run: code-guard . --ci
       - run: code-guard --help
       - run: python -c "from pathlib import Path; Path('package-smoke.py').write_text('value = 1\n', encoding='utf-8')"
       - run: code-guard package-smoke.py --json
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 40b99fe..f7bd3bf 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -6,6 +6,8 @@ Notable changes to Agent Code Guard are recorded here.
 
 ### Added
 
+- Zero-baseline CI dogfooding through the installed console command, with visible
+  non-blocking REVIEW findings and blocking FAIL findings or tool errors.
 - Source-controlled, non-increasing LOC ratchet creation, automatic analysis,
   and explicit lowering/pruning for established legacy repositories.
 - Read-only `code-guard doctor` human and JSON diagnostics for the active
diff --git a/README.md b/README.md
index dd9a910..6c521c0 100644
--- a/README.md
+++ b/README.md
@@ -11,6 +11,10 @@ Deterministic guardrails for agent-assisted software development.
 [![Python 3.10–3.14](https://img.shields.io/badge/Python-3.10%E2%80%933.14-3776AB?logo=python&logoColor=white)](https://github.com/stef-k/agent-code-guard/blob/main/docs/platform-support.md)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/stef-k/agent-code-guard/blob/main/LICENSE)
 
+CI installs Agent Code Guard and analyzes its own real checkout. REVIEW findings
+remain visible but non-blocking, while FAIL findings and tool errors block the
+workflow; the repository intentionally uses no LOC baseline.
+
 Code Guard gives coding agents objective measurements and **PASS / REVIEW /
 FAIL** signals while leaving design decisions to agent and user judgment.