ajianaz · Jun 11, 2026 · Jun 11, 2026
diff --git a/.agent.md b/.agent.md
@@ -8,7 +8,7 @@ Before creating any release PR, verify ALL of the following are updated:
 
 - [ ] `Cargo.toml` — version bump
 - [ ] All target issues merged to `develop`
-- [ ] `cargo test` — all 453+ tests pass
+- [ ] `cargo test` — all 485+ tests pass
 - [ ] `cargo clippy --all-targets -- -D warnings` — clean
 - [ ] `cargo fmt --all -- --check` — clean
 - [ ] `cargo build --release` — no errors

diff --git a/AGENT.md b/AGENT.md
@@ -17,7 +17,7 @@ no managed API, no cloud service. Runs locally against diffs, scans, or branches
 ```bash
 cargo build              # Build (debug)
 cargo build --release    # Build (release)
-cargo test               # Run all 453 tests
+cargo test               # Run all 485 tests
 cargo clippy --all-targets -- -D warnings  # Lint (strict)
 cargo fmt --all -- --check  # Format check
 ```
@@ -39,6 +39,7 @@ src/
 │   ├── init.rs          # cora init (project scaffolding)
 │   ├── upload.rs        # cora upload (review upload)
 │   ├── completion.rs    # Shell completion generation
+│   ├── debt.rs          # cora debt (tech debt report)
 │   └── providers.rs     # cora providers (list providers)
 ├── config/
 │   ├── mod.rs
@@ -58,6 +59,7 @@ src/
 │   ├── security_scanner.rs  # Static security pattern matching
 │   ├── language_analyzer.rs # Language-specific review guidance
 │   ├── secrets_scanner.rs   # Secret/credential detection
+│   ├── debt_tracker.rs  # Tech debt metrics + history snapshots
 │   └── rules/           # Custom rule engine
 │       ├── mod.rs
 │       ├── builtin.rs   # Built-in rules
@@ -96,8 +98,8 @@ src/
 ## Testing
 
 ```bash
-cargo test               # 453 tests total
-                         #   431 unit tests
+cargo test               # 485 tests total
+                         #   463 unit tests
                          #    16 CLI integration tests
                          #     6 config tests
 cargo test --no-verify   # Skip pre-commit hooks (avoids timeout in hooks)

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -37,6 +37,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **Auto-chunking** — large diffs split into reviewable chunks automatically (#188)
   - `--no-auto-chunk` flag to disable
   - `src/engine/chunker.rs` module (~310 lines)
+- **Tech debt metrics** — cumulative review history and trend tracking (#206)
+  - `DebtSnapshot` per-review JSON snapshots with quality score (0-10)
+  - `cora debt` subcommand — terminal table, `--json`, `--trend` ASCII graph, `--since`, `--branch` filters
+  - Auto-save after every review (best-effort, never fails review)
+  - `debt:` config section in `.cora.yaml` (history_dir, retention_days)
+  - 32 unit tests
 - **Multi-platform CI docs** — Gitea/Forgejo, GitLab CI, Bitbucket Pipelines workflow examples (#225)
 - **GitHub Marketplace action** — published as [`codecoradev/cora-review-action@v1`](https://github.com/marketplace/actions/cora-ai-code-review)
 - **Improved review prompt** — better consistency, lower false-negative rate, explicit error handling focus area

diff --git a/README.md b/README.md
@@ -137,6 +137,7 @@ Works on **all CI platforms** — [Gitea, GitLab, Bitbucket →](https://codecor
 | `cora auth login` | Save API key |
 | `cora config show` | Show resolved config |
 | `cora providers` | List available LLM providers |
+| `cora debt` | Show tech debt report from review history |
 | `cora mcp` | Start MCP server for AI coding agents |
 | `cora hook install` | Install pre-commit hook |
 

diff --git a/docs/changelog.md b/docs/changelog.md
@@ -37,6 +37,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **Auto-chunking** — large diffs split into reviewable chunks automatically (#188)
   - `--no-auto-chunk` flag to disable
   - `src/engine/chunker.rs` module (~310 lines)
+- **Tech debt metrics** — cumulative review history and trend tracking (#206)
+  - `DebtSnapshot` per-review JSON snapshots with quality score (0-10)
+  - `cora debt` subcommand — terminal table, `--json`, `--trend` ASCII graph, `--since`, `--branch` filters
+  - Auto-save after every review (best-effort, never fails review)
+  - `debt:` config section in `.cora.yaml` (history_dir, retention_days)
+  - 32 unit tests
 - **Multi-platform CI docs** — Gitea/Forgejo, GitLab CI, Bitbucket Pipelines workflow examples (#225)
 - **GitHub Marketplace action** — published as [`codecoradev/cora-review-action@v1`](https://github.com/marketplace/actions/cora-ai-code-review)
 - **Improved review prompt** — better consistency, lower false-negative rate, explicit error handling focus area

diff --git a/docs/cli-reference.md b/docs/cli-reference.md
@@ -47,6 +47,11 @@ Complete command reference for the cora CLI.
 | `cora upload-sarif` `<file>` | Upload SARIF to GitHub Code Scanning |
 | `cora completion` `<shell>` | Generate shell completions (bash/zsh/fish) |
 | `cora mcp` | Start MCP server for AI coding agents (Claude Code, Cursor, Windsurf) |
+| `cora debt` | Show tech debt report from review history |
+| `cora debt --json` | Debt report in JSON format |
+| `cora debt --trend` | Quality score trend graph |
+| `cora debt --since <date\|tag>` | Filter by date or git tag |
+| `cora debt --branch <name>` | Filter by branch name |
 
 ## Quick Examples
 

diff --git a/docs/configuration.md b/docs/configuration.md
@@ -307,6 +307,32 @@ rules:
 
 Rules run during the deterministic pre-scan phase (no LLM needed).
 
+## Tech Debt Tracker
+
+cora tracks review history and calculates tech debt metrics over time.
+
+### Config
+
+```yaml
+debt:
+  enabled: true           # default: true
+  history_dir: .cora/history  # snapshot storage
+  retention_days: 90      # auto-cleanup old snapshots
+```
+
+### CLI
+
+```bash
+cora debt                    # Show debt report table
+cora debt --json             # Machine-readable JSON output
+cora debt --trend            # ASCII quality score graph
+cora debt --since 2026-06-01 # Filter by date
+cora debt --since v0.4.5     # Filter by git tag
+cora debt --branch develop   # Filter by branch
+```
+
+Snapshots are auto-saved after every review (best-effort, never fails the review).
+
 ## MCP Server
 
 cora includes a built-in MCP (Model Context Protocol) server that exposes rules and config to AI coding agents like Claude Code, Cursor, Copilot, and Windsurf.

diff --git a/docs/roadmap.md b/docs/roadmap.md
@@ -71,7 +71,7 @@ Demand-gated — we build what people actually need. Track progress on [GitHub I
 - [#207](https://github.com/codecoradev/cora-cli/issues/207) MCP server — expose rules to AI agents — ✓ Done
 - [#238](https://github.com/codecoradev/cora-cli/issues/238) Quality profiles bug fix — path resolution, fail-fast, dedup — ✓ Done
 - [#188](https://github.com/codecoradev/cora-cli/issues/188) Auto-chunking for large diffs — ✓ Done
-- [#206](https://github.com/codecoradev/cora-cli/issues/206) Tech debt metrics — review history — ◎ Planned
+- [#206](https://github.com/codecoradev/cora-cli/issues/206) Tech debt metrics — review history — ✓ Done
 
 ## v0.6 — Growth & Marketplace