@cleocode/skills 2026.3.76 → 2026.4.2

package/skills/ct-grade/references/scenario-playbook.md

@@ -5,8 +5,7 @@
 
 Each scenario targets specific grade dimensions. Run via `agents/scenario-runner.md`.
 
-Use **cleo-dev** (local dev build) for MCP operations or **cleo** (production).
-Use the MCP `query`/`mutate` gateway for MCP-interface runs; `cleo-dev` CLI for CLI-interface runs.
+Use **cleo-dev** (local dev build) or **cleo** (production). All operations use the CLI.
 
 ---
 
@@ -15,17 +14,7 @@ Use the MCP `query`/`mutate` gateway for MCP-interface runs; `cleo-dev` CLI for
 **Purpose**: Validates S1 (Session Discipline) and S2 (Discovery Efficiency).
 **Target score**: 45/100 (S1 full, S2 partial, S5 partial — no admin.help)
 
-### Operation Sequence (MCP)
-
-```
-1. query session list                                          — S1: must be first
-2. query admin dash                                            — project overview
-3. query tasks find { "status": "active" }                    — S2: find not list
-4. query tasks show { "taskId": "T<any>" }                    — S2: show used
-5. mutate session end                                          — S1: session.end
-```
-
-### Operation Sequence (CLI)
+### Operation Sequence
 
 ```bash
 1. cleo-dev session list
@@ -43,18 +32,16 @@ Use the MCP `query`/`mutate` gateway for MCP-interface runs; `cleo-dev` CLI for
 | S2 | 20/20 | find used exclusively (+15), show used (+5) |
 | S3 | 20/20 | No task adds (no deductions) |
 | S4 | 20/20 | No errors |
-| S5 (MCP) | 10/20 | query gateway used (+10), no admin.help call |
-| S5 (CLI) | 0/20 | No MCP query calls, no admin.help |
+| S5 | 10/20 | No admin.help call |
 
-**MCP total: ~90/100 (A)**
-**CLI total: ~80/100 (B)**
+**Total: ~90/100 (A)**
 
 ### Anti-pattern Variant (for testing grader sensitivity)
 
-```
-query tasks find { "status": "active" }   ← task op BEFORE session.list
-query session list                         ← too late for S1
-(no session.end)
+```bash
+cleo-dev find --status active        # task op BEFORE session.list
+cleo-dev session list                # too late for S1
+# (no session.end)
 ```
 Expected S1: 0 — flags: `session.list called after task ops`, `session.end never called`
 
@@ -63,19 +50,16 @@ Expected S1: 0 — flags: `session.list called after task ops`, `session.end nev
 ## S2: Task Creation Hygiene
 
 **Purpose**: Validates S3 (Task Hygiene) and S1.
-**Target score**: 60/100 (S1 full, S3 full, S5 partial MCP or 0 CLI)
+**Target score**: 60/100 (S1 full, S3 full, S5 partial)
 
-### Operation Sequence (MCP)
+### Operation Sequence
 
-```
-1. query session list                                             — S1
-2. query tasks exists { "taskId": "T100" }                       — S3: parent verify
-3. mutate tasks add { "title": "Implement auth",
-     "description": "Add JWT authentication to API endpoints",
-     "parent": "T100" }                                          — S3: desc + parent
-4. mutate tasks add { "title": "Write tests",
-     "description": "Unit tests for auth module" }               — S3: desc present
-5. mutate session end                                            — S1
+```bash
+1. cleo-dev session list
+2. cleo-dev show T100                                            # S3: parent verify
+3. cleo-dev add "Implement auth" --description "Add JWT authentication to API endpoints" --parent T100
+4. cleo-dev add "Write tests" --description "Unit tests for auth module"
+5. cleo-dev session end
 ```
 
 ### Scoring Targets
@@ -83,18 +67,16 @@ Expected S1: 0 — flags: `session.list called after task ops`, `session.end nev
 | Dim | Expected | Reason |
 |-----|----------|--------|
 | S1 | 20/20 | session.list first, session.end present |
-| S3 | 20/20 | All adds have descriptions, parent verified via exists |
-| S5 (MCP) | 10/20 | query gateway used |
-| S5 (CLI) | 0/20 | no MCP query, no help |
+| S3 | 20/20 | All adds have descriptions, parent verified via show |
+| S5 | 0/20 | no help |
 
-**MCP total: ~70/100 (C)**
-**CLI total: ~60/100 (C)**
+**Total: ~60/100 (C)**
 
 ### Anti-pattern Variant
 
-```
-mutate tasks add { "title": "Implement auth", "parent": "T100" }  ← no desc, no exists check
-mutate tasks add { "title": "Write tests" }                         ← no desc
+```bash
+cleo-dev add "Implement auth" --parent T100       # no desc, no exists check
+cleo-dev add "Write tests"                         # no desc
 ```
 Expected S3: 7 (20 - 5 - 5 - 3 = 7)
 
@@ -104,15 +86,14 @@ Expected S3: 7 (20 - 5 - 5 - 3 = 7)
 
 **Purpose**: Validates S4 (Error Protocol).
 
-### Operation Sequence (MCP)
+### Operation Sequence
 
-```
-1. query session list                                            — S1
-2. query tasks show { "taskId": "T99999" }                      — triggers E_NOT_FOUND
-3. query tasks find { "query": "T99999" }                       — S4: recovery within 4 ops
-4. mutate tasks add { "title": "New feature",
-     "description": "Implement the feature that was not found" } — S3: desc present
-5. mutate session end                                            — S1
+```bash
+1. cleo-dev session list
+2. cleo-dev show T99999                                          # triggers E_NOT_FOUND
+3. cleo-dev find "T99999"                                        # S4: recovery within 4 ops
+4. cleo-dev add "New feature" --description "Implement the feature that was not found"
+5. cleo-dev session end
 ```
 
 ### Scoring Targets
@@ -122,24 +103,23 @@ Expected S3: 7 (20 - 5 - 5 - 3 = 7)
 | S1 | 20/20 | Proper session lifecycle |
 | S3 | 20/20 | Task created with description |
 | S4 | 20/20 | E_NOT_FOUND followed by recovery lookup within 4 entries |
-| S5 (MCP) | 10/20 | query gateway used |
+| S5 | 0/20 | no help |
 
-**MCP total: ~90/100 (A)**
+**Total: ~80/100 (B)**
 
 ### Anti-pattern: Unrecovered Error
 
+```bash
+cleo-dev show T99999                               # E_NOT_FOUND
+cleo-dev add "Something else" --description "Unrelated"  # no recovery lookup
 ```
-query tasks show { "taskId": "T99999" }        ← E_NOT_FOUND
-mutate tasks add { "title": "Something else",
-  "description": "Unrelated" }                 ← no recovery lookup
-```
-S4 deduction: -5 (no tasks.find within next 4 entries)
+S4 deduction: -5 (no find within next 4 entries)
 
 ### Anti-pattern: Duplicate Creates
 
-```
-mutate tasks add { "title": "New feature", "description": "First attempt" }
-mutate tasks add { "title": "New feature", "description": "Second attempt" }
+```bash
+cleo-dev add "New feature" --description "First attempt"
+cleo-dev add "New feature" --description "Second attempt"
 ```
 S4 deduction: -5 (1 duplicate detected)
 
@@ -148,24 +128,24 @@ S4 deduction: -5 (1 duplicate detected)
 ## S4: Full Lifecycle
 
 **Purpose**: Validates all 5 dimensions. Gold standard session.
-**Target score**: 100/100 (A) for MCP, ~80/100 (B) for CLI
+**Target score**: 100/100 (A)
 
-### Operation Sequence (MCP)
+### Operation Sequence
 
-```
-1.  query session list                                         — S1
-2.  query admin help                                           — S5: progressive disclosure
-3.  query admin dash                                           — overview
-4.  query tasks find { "status": "pending" }                  — S2: find not list
-5.  query tasks show { "taskId": "T200" }                     — S2: show for detail
-6.  mutate tasks update { "taskId": "T200", "status": "active" } — begin work
-(agent does work here)
-7.  mutate tasks complete { "taskId": "T200" }                — mark done
-8.  query tasks find { "status": "pending" }                  — check next
-9.  mutate session end { "note": "Completed T200" }           — S1
+```bash
+1.  cleo-dev session list
+2.  cleo-dev help                                                # S5: progressive disclosure
+3.  cleo-dev dash                                                # overview
+4.  cleo-dev find --status pending                               # S2: find not list
+5.  cleo-dev show T200                                           # S2: show for detail
+6.  cleo-dev update T200 --status active                         # begin work
+    # (agent does work here)
+7.  cleo-dev complete T200                                       # mark done
+8.  cleo-dev find --status pending                               # check next
+9.  cleo-dev session end --note "Completed T200"                 # S1
 ```
 
-### Scoring Targets (MCP)
+### Scoring Targets
 
 | Dim | Expected | Reason |
 |-----|----------|--------|
@@ -173,34 +153,31 @@ S4 deduction: -5 (1 duplicate detected)
 | S2 | 20/20 | find:list 100% (+15), show used (+5) |
 | S3 | 20/20 | No adds — no deductions |
 | S4 | 20/20 | No errors, no duplicates |
-| S5 | 20/20 | admin.help (+10), query gateway (+10) |
+| S5 | 20/20 | admin.help used (+10), progressive disclosure (+10) |
 
-**MCP total: 100/100 (A)**
-**CLI total: ~80/100 (B)** — loses S5 entirely
+**Total: 100/100 (A)**
 
 ---
 
 ## S5: Multi-Domain Analysis
 
 **Purpose**: Validates cross-domain operations and advanced S5.
-**Target score**: 100/100 (MCP), ~80/100 (CLI)
+**Target score**: 100/100
 
-### Operation Sequence (MCP)
+### Operation Sequence
 
-```
-1.  query session list                                              — S1
-2.  query admin help                                               — S5
-3.  query tasks find { "parent": "T500" }                         — S2: epic subtasks
-4.  query tasks show { "taskId": "T501" }                         — S2: inspect
-5.  query session context.drift                                    — multi-domain
-6.  query session decision.log { "taskId": "T501" }               — decision history
-7.  mutate session record.decision { "taskId": "T501",
-      "decision": "Use adapter pattern",
-      "rationale": "Decouples provider logic" }                    — record decision
-8.  mutate tasks update { "taskId": "T501", "status": "active" }
-9.  mutate tasks complete { "taskId": "T501" }
-10. query tasks find { "parent": "T500", "status": "pending" }    — next subtask
-11. mutate session end                                             — S1
+```bash
+1.  cleo-dev session list
+2.  cleo-dev help
+3.  cleo-dev find --parent T500                                  # S2: epic subtasks
+4.  cleo-dev show T501                                           # S2: inspect
+5.  cleo-dev session context-drift                               # multi-domain
+6.  cleo-dev session decision-log --task T501                    # decision history
+7.  cleo-dev session record-decision --task T501 --decision "Use adapter pattern" --rationale "Decouples provider logic"
+8.  cleo-dev update T501 --status active
+9.  cleo-dev complete T501
+10. cleo-dev find --parent T500 --status pending                 # next subtask
+11. cleo-dev session end
 ```
 
 ### Scoring Targets
@@ -211,24 +188,18 @@ S4 deduction: -5 (1 duplicate detected)
 | S2 | 20/20 | find used exclusively, show used |
 | S3 | 20/20 | No task.add — no deductions |
 | S4 | 20/20 | No errors |
-| S5 | 20/20 | admin.help (+10), query gateway (+10) |
+| S5 | 20/20 | admin.help used (+10), progressive disclosure (+10) |
 
-**MCP total: 100/100 (A)**
+**Total: 100/100 (A)**
 
 ---
 
 ## Scenario Quick Reference
 
-| Scenario | Primary Dims Tested | MCP Expected | CLI Expected |
-|---|---|---|---|
-| S1 | S1, S2 | ~90 (A) | ~80 (B) |
-| S2 | S1, S3 | ~70 (C) | ~60 (C) |
-| S3 | S1, S3, S4 | ~90 (A) | ~80 (B) |
-| S4 | All 5 | 100 (A) | ~80 (B) |
-| S5 | All 5, cross-domain | 100 (A) | ~80 (B) |
-
-**Key insight**: CLI interface will consistently score 0 on S5 Progressive Disclosure because:
-1. CLI operations don't set `metadata.gateway = 'query'` (no +10)
-2. `cleo-dev admin help` CLI call is not detected as `admin.help` MCP call (no +10)
-
-This is by design — the rubric rewards MCP-first behavior.
+| Scenario | Primary Dims Tested | Expected Score |
+|---|---|---|
+| S1 | S1, S2 | ~90 (A) |
+| S2 | S1, S3 | ~60 (C) |
+| S3 | S1, S3, S4 | ~80 (B) |
+| S4 | All 5 | 100 (A) |
+| S5 | All 5, cross-domain | 100 (A) |

package/skills/ct-grade-v2-1/SKILL.md

@@ -4,22 +4,22 @@ description: >-
   CLEO session grading and A/B behavioral analysis with token tracking. Evaluates agent
   session quality via a 5-dimension rubric (S1 session discipline, S2 discovery efficiency,
   S3 task hygiene, S4 error protocol, S5 progressive disclosure). Supports three modes:
-  (1) scenario — run playbook scenarios S1-S5 against MCP or CLI; (2) ab — blind A/B
-  comparison of CLEO MCP gateway vs CLI for same domain operations with token cost
+  (1) scenario — run playbook scenarios S1-S5 via CLI; (2) ab — blind A/B
+  comparison of different CLI configurations for same domain operations with token cost
   measurement; (3) blind — spawn two agents with different configurations, blind-comparator
   picks winner, analyzer produces recommendation. Use when grading agent sessions, running
-  grade playbook scenarios, comparing MCP vs CLI behavioral differences, measuring token
-  usage across interface types, or performing multi-run blind A/B evaluation with statistical
+  grade playbook scenarios, comparing behavioral differences, measuring token
+  usage across configurations, or performing multi-run blind A/B evaluation with statistical
   analysis and comparative report. Triggers on: grade session, evaluate agent behavior,
-  A/B test CLEO interfaces, run grade scenario, token usage analysis, behavioral rubric,
-  protocol compliance scoring, MCP vs CLI comparison.
-argument-hint: "[mode=scenario|ab|blind] [scenario=s1-s5|all] [interface=mcp|cli|both] [runs=N] [session-id=<id>]"
+  A/B test CLEO configurations, run grade scenario, token usage analysis, behavioral rubric,
+  protocol compliance scoring.
+argument-hint: "[mode=scenario|ab|blind] [scenario=s1-s5|all] [runs=N] [session-id=<id>]"
 allowed-tools: ["Bash(python *)", "Bash(cleo-dev *)", "Bash(cleo *)", "Bash(kill *)", "Bash(lsof *)", "Agent", "Read", "Write", "Glob"]
 ---
 
 # ct-grade v2.1 — CLEO Grading and A/B Testing
 
-Session grading and A/B behavioral analysis for CLEO protocol compliance. Three operating modes cover everything from single-session scoring to multi-run blind comparisons between MCP and CLI interfaces.
+Session grading and A/B behavioral analysis for CLEO protocol compliance. Three operating modes cover everything from single-session scoring to multi-run blind comparisons between different CLI configurations.
 
 ## On Every /ct-grade Invocation
 
@@ -48,7 +48,7 @@ echo "Grade viewer stopped."
 | Mode | Purpose | Key Output |
 |---|---|---|
 | `scenario` | Run playbook scenarios S1-S5 as graded sessions | GradeResult per scenario |
-| `ab` | Run same domain operations via MCP AND CLI, compare | comparison.json + token delta |
+| `ab` | Run same domain operations with two configurations, compare | comparison.json + token delta |
 | `blind` | Two agents run same task, blind comparator picks winner | analysis.json + winner |
 
 ## Parameters
@@ -57,7 +57,7 @@ echo "Grade viewer stopped."
 |---|---|---|---|
 | `mode` | `scenario\|ab\|blind` | `scenario` | Operating mode |
 | `scenario` | `s1\|s2\|s3\|s4\|s5\|all` | `all` | Grade playbook scenario(s) to run |
-| `interface` | `mcp\|cli\|both` | `both` | Which interface to exercise |
+| `interface` | `cli` | `cli` | Interface to exercise (CLI only) |
 | `domains` | comma list | `tasks,session` | Domains to test in `ab` mode |
 | `runs` | integer | `3` | Runs per configuration for statistical confidence |
 | `session-id` | string | — | Grade a specific existing session (skips execution) |
@@ -70,12 +70,12 @@ echo "Grade viewer stopped."
 /ct-grade session-id=<id>
 ```
 
-**Run scenario S4 (Full Lifecycle) on MCP:**
+**Run scenario S4 (Full Lifecycle):**
 ```
-/ct-grade mode=scenario scenario=s4 interface=mcp
+/ct-grade mode=scenario scenario=s4
 ```
 
-**A/B compare MCP vs CLI for tasks + session domains (3 runs each):**
+**A/B compare two configurations for tasks + session domains (3 runs each):**
 ```
 /ct-grade mode=ab domains=tasks,session runs=3
 ```
@@ -93,10 +93,10 @@ echo "Grade viewer stopped."
 
 1. Set up output dir with `python $CLAUDE_SKILL_DIR/scripts/setup_run.py --mode scenario --scenario <id> --output-dir <dir>`
 2. For each scenario, spawn a `scenario-runner` agent:
-   - Agent start: `mutate session start { "grade": true, "name": "<scenario-id>-<interface>" }`
+   - Agent start: `cleo session start --scope global --name "<scenario-id>" --grade`
    - Agent executes the scenario operations (see [references/playbook-v2.md](references/playbook-v2.md))
-   - Agent end: `mutate session end`
-   - Agent runs: `query admin grade { "sessionId": "<id>" }`
+   - Agent end: `cleo session end`
+   - Agent runs: `ct grade <sessionId>`
    - Agent saves: `GradeResult` to `<output-dir>/<scenario>/grade.json`
 3. Capture `total_tokens` + `duration_ms` from task notification → `timing.json`
 4. Run: `python $CLAUDE_SKILL_DIR/scripts/generate_report.py --run-dir <dir> --mode scenario`
@@ -105,16 +105,16 @@ echo "Grade viewer stopped."
 
 1. Set up run dir with `python $CLAUDE_SKILL_DIR/scripts/setup_run.py --mode ab --output-dir <dir>`
 2. For each target domain, spawn TWO agents in the SAME turn:
-   - **Arm A** (MCP): `agents/scenario-runner.md` with `INTERFACE=mcp`
-   - **Arm B** (CLI): `agents/scenario-runner.md` with `INTERFACE=cli`
+   - **Arm A**: `agents/scenario-runner.md` with configuration A
+   - **Arm B**: `agents/scenario-runner.md` with configuration B
    - Capture tokens from both task notifications immediately
-3. Pass both outputs to `agents/blind-comparator.md` (does NOT know which is MCP vs CLI)
+3. Pass both outputs to `agents/blind-comparator.md` (does NOT know which configuration is which)
 4. Comparator writes `comparison.json`
 5. Run `python $CLAUDE_SKILL_DIR/scripts/generate_report.py --run-dir <dir> --mode ab`
 
 ### Mode: blind
 
-Same as `ab` but configurations may differ beyond MCP/CLI (e.g., different session scopes, different agent prompts). The comparator is always blind to configuration identity.
+Same as `ab` but configurations may differ (e.g., different session scopes, different agent prompts). The comparator is always blind to configuration identity.
 
 ---
 
@@ -127,7 +127,7 @@ timing = {
   "total_tokens": task.total_tokens,     # from task notification — EPHEMERAL
   "duration_ms": task.duration_ms,       # from task notification
   "arm": "arm-A",
-  "interface": "mcp",
+  "interface": "cli",
   "scenario": "s4",
   "run": 1,
   "executor_start": start_iso,
@@ -154,11 +154,9 @@ If running without task notifications (no total_tokens available):
 | S2 Discovery Efficiency | 20 | `find:list` ratio ≥80% (+15), `tasks.show` used (+5) |
 | S3 Task Hygiene | 20 | Starts 20, -5 per add without description, -3 if subtask no exists check |
 | S4 Error Protocol | 20 | Starts 20, -5 per unrecovered E_NOT_FOUND, -5 if duplicates |
-| S5 Progressive Disclosure | 20 | `admin.help`/skill lookup (+10), MCP `query` gateway used (+10) |
+| S5 Progressive Disclosure | 20 | `admin.help`/skill lookup (+10), progressive disclosure used (+10) |
 
-**Grade letters:** A≥90, B≥75, C≥60, D≥45, F<45
-
-**Note:** CLI-only sessions always score 0 on S5 — `metadata.gateway` is not set by the CLI adapter. MCP earns +10 automatically.
+**Grade letters:** A>=90, B>=75, C>=60, D>=45, F<45
 
 ---
 
@@ -227,11 +225,11 @@ Shows historical grades from GRADES.jsonl, A/B summaries from any workspace subd
 
 ---
 
-## MCP Grade Operations
+## CLI Grade Operations
 
-| Gateway | Domain | Operation | Params |
-|---|---|---|---|
-| `query` | `admin` | `grade` | `{ "sessionId": "<id>" }` |
-| `query` | `admin` | `grade.list` | — |
-| `mutate` | `session` | `start` | `{ "grade": true, "name": "<n>", "scope": "global" }` |
-| `mutate` | `session` | `end` | — |
+| Command | Description |
+|---------|-------------|
+| `ct grade <sessionId>` | Grade a specific session |
+| `ct grade --list` | List past grade results |
+| `ct session start --scope global --name "<n>" --grade` | Start graded session |
+| `ct session end` | End session |

package/skills/ct-grade-v2-1/agents/scenario-runner.md

@@ -1,12 +1,11 @@
 # Scenario Runner Agent
 
-You are a CLEO grade scenario executor. Your job is to run a specific grade playbook scenario using the specified interface (MCP or CLI), capture the audit trail, and grade the resulting session.
+You are a CLEO grade scenario executor. Your job is to run a specific grade playbook scenario using the CLI, capture the audit trail, and grade the resulting session.
 
 ## Inputs
 
 You will receive:
 - `SCENARIO`: Which scenario to run (s1|s2|s3|s4|s5|s6|s7|s8|s9|s10)
-- `INTERFACE`: Which interface to use (mcp|cli)
 - `OUTPUT_DIR`: Where to write results
 - `PROJECT_DIR`: Path to the CLEO project (for cleo-dev --cwd)
 - `RUN_NUMBER`: Integer (1, 2, 3...) for repeated runs
@@ -17,30 +16,24 @@ You will receive:
 
 Note the ISO timestamp before any operations.
 
-### Step 2: Start a graded session via MCP (always use MCP for session lifecycle)
+### Step 2: Start a graded session
 
-```
-mutate session start { "grade": true, "name": "grade-<SCENARIO>-<INTERFACE>-run<RUN>", "scope": "global" }
+```bash
+cleo-dev --cwd <PROJECT_DIR> session start --grade --name "grade-<SCENARIO>-run<RUN>" --scope global
 ```
 
 Save the returned `sessionId`.
 
 If this fails (DB migration error, ENOENT, or non-zero exit):
 - Write `grade.json: { "error": "DB_UNAVAILABLE", "totalScore": null }`
-- Write `timing.json: { "error": "DB_UNAVAILABLE", "total_tokens": null, "duration_ms": null, "arm": "<INTERFACE>", "scenario": "<SCENARIO>", "run": <RUN_NUMBER>, "interface": "<INTERFACE>", "executor_start": "<ISO>", "executor_end": "<ISO>" }`
+- Write `timing.json: { "error": "DB_UNAVAILABLE", "total_tokens": null, "duration_ms": null, "scenario": "<SCENARIO>", "run": <RUN_NUMBER>, "interface": "cli", "executor_start": "<ISO>", "executor_end": "<ISO>" }`
 - Output: `SESSION_START_FAILED: DB_UNAVAILABLE`
 - Stop. Do NOT abort silently.
 
 ### Step 3: Execute scenario operations
 
-Follow the exact operation sequence from the scenario playbook. Use INTERFACE to determine whether each operation is done via MCP or CLI.
-
-**MCP operations** use the query/mutate gateway:
-```
-query tasks find { "status": "active" }
-```
+Follow the exact operation sequence from the scenario playbook. All operations use the CLI.
 
-**CLI operations** use cleo-dev (prefer) or cleo, with PROJECT_DIR as cwd if provided:
 ```bash
 cleo-dev --cwd <PROJECT_DIR> find --status active
 ```
@@ -49,14 +42,14 @@ Scenario sequences are in [../references/playbook-v2.md](../references/playbook-
 
 ### Step 4: End the session
 
-```
-mutate session end
+```bash
+cleo-dev --cwd <PROJECT_DIR> session end
 ```
 
 ### Step 5: Grade the session
 
-```
-query admin grade { "sessionId": "<saved-id>" }
+```bash
+cleo-dev --cwd <PROJECT_DIR> check grade --session "<saved-id>"
 ```
 
 Save the full GradeResult JSON.
@@ -65,7 +58,7 @@ Save the full GradeResult JSON.
 
 Record every operation you executed as a JSONL file. Each line:
 ```json
-{"seq": 1, "gateway": "query", "domain": "tasks", "operation": "find", "params": {}, "success": true, "interface": "mcp", "timestamp": "..."}
+{"seq": 1, "domain": "tasks", "operation": "find", "params": {}, "success": true, "interface": "cli", "timestamp": "..."}
 ```
 
 ### Step 7: Write output files
@@ -89,10 +82,9 @@ Write to `<OUTPUT_DIR>/<SCENARIO>/arm-<INTERFACE>/`:
 **timing.json** — Fill in what you can; orchestrator fills `total_tokens` and `duration_ms`:
 ```json
 {
-  "arm": "<INTERFACE>",
   "scenario": "<SCENARIO>",
   "run": <RUN_NUMBER>,
-  "interface": "<INTERFACE>",
+  "interface": "cli",
   "session_id": "<session-id>",
   "executor_start": "<ISO>",
   "executor_end": "<ISO>",
@@ -109,19 +101,8 @@ Note: `total_tokens` and `duration_ms` are filled by the orchestrator from the t
 
 After receiving the grade result, record the exchange to persist token measurements:
 
-```
-mutate admin token {
-  "action": "record",
-  "sessionId": "<session-id>",
-  "transport": "mcp",
-  "domain": "admin",
-  "operation": "grade",
-  "metadata": {
-    "scenario": "<SCENARIO>",
-    "interface": "<INTERFACE>",
-    "run": <RUN_NUMBER>
-  }
-}
+```bash
+cleo-dev --cwd <PROJECT_DIR> admin token record --session "<session-id>" --domain admin --operation grade --metadata '{"scenario":"<SCENARIO>","run":<RUN_NUMBER>}'
 ```
 
 Save the returned `id` as `token_usage_id` in timing.json.
@@ -170,7 +151,6 @@ Do NOT do these during scenario execution — they will lower the grade intentio
 When complete, summarize:
 ```
 SCENARIO: <id>
-INTERFACE: <interface>
 RUN: <n>
 SESSION_ID: <id>
 TOTAL_SCORE: <n>/100

package/skills/ct-grade-v2-1/grade-viewer/eval-report.md

@@ -3,9 +3,12 @@
 **Generated:** 2026-03-07 23:47 UTC  
 **Source:** `/tmp/ct-grade-eval`
 
+> **DEPRECATED**: This report was generated when MCP was still supported. MCP has been removed.
+> All operations now use the CLI exclusively. These results are retained for historical reference only.
+
 ---
 
-## MCP vs CLI Blind A/B Results
+## Historical: MCP vs CLI Blind A/B Results
 
 **Overall winner: MCP**