@complexthings/superpowers-agent 9.2.1 → 10.0.1

package/.agents/skills/skill-creator/scripts/run_loop.py

@@ -0,0 +1,328 @@
+#!/usr/bin/env python3
+"""Run the eval + improve loop until all pass or max iterations reached.
+
+Combines run_eval.py and improve_description.py in a loop, tracking history
+and returning the best description found. Supports train/test split to prevent
+overfitting.
+"""
+
+import argparse
+import json
+import random
+import sys
+import tempfile
+import time
+import webbrowser
+from pathlib import Path
+
+from scripts.generate_report import generate_html
+from scripts.improve_description import improve_description
+from scripts.run_eval import find_project_root, run_eval
+from scripts.utils import parse_skill_md
+
+
+def split_eval_set(eval_set: list[dict], holdout: float, seed: int = 42) -> tuple[list[dict], list[dict]]:
+    """Split eval set into train and test sets, stratified by should_trigger."""
+    random.seed(seed)
+
+    # Separate by should_trigger
+    trigger = [e for e in eval_set if e["should_trigger"]]
+    no_trigger = [e for e in eval_set if not e["should_trigger"]]
+
+    # Shuffle each group
+    random.shuffle(trigger)
+    random.shuffle(no_trigger)
+
+    # Calculate split points
+    n_trigger_test = max(1, int(len(trigger) * holdout))
+    n_no_trigger_test = max(1, int(len(no_trigger) * holdout))
+
+    # Split
+    test_set = trigger[:n_trigger_test] + no_trigger[:n_no_trigger_test]
+    train_set = trigger[n_trigger_test:] + no_trigger[n_no_trigger_test:]
+
+    return train_set, test_set
+
+
+def run_loop(
+    eval_set: list[dict],
+    skill_path: Path,
+    description_override: str | None,
+    num_workers: int,
+    timeout: int,
+    max_iterations: int,
+    runs_per_query: int,
+    trigger_threshold: float,
+    holdout: float,
+    model: str,
+    verbose: bool,
+    live_report_path: Path | None = None,
+    log_dir: Path | None = None,
+) -> dict:
+    """Run the eval + improvement loop."""
+    project_root = find_project_root()
+    name, original_description, content = parse_skill_md(skill_path)
+    current_description = description_override or original_description
+
+    # Split into train/test if holdout > 0
+    if holdout > 0:
+        train_set, test_set = split_eval_set(eval_set, holdout)
+        if verbose:
+            print(f"Split: {len(train_set)} train, {len(test_set)} test (holdout={holdout})", file=sys.stderr)
+    else:
+        train_set = eval_set
+        test_set = []
+
+    history = []
+    exit_reason = "unknown"
+
+    for iteration in range(1, max_iterations + 1):
+        if verbose:
+            print(f"\n{'='*60}", file=sys.stderr)
+            print(f"Iteration {iteration}/{max_iterations}", file=sys.stderr)
+            print(f"Description: {current_description}", file=sys.stderr)
+            print(f"{'='*60}", file=sys.stderr)
+
+        # Evaluate train + test together in one batch for parallelism
+        all_queries = train_set + test_set
+        t0 = time.time()
+        all_results = run_eval(
+            eval_set=all_queries,
+            skill_name=name,
+            description=current_description,
+            num_workers=num_workers,
+            timeout=timeout,
+            project_root=project_root,
+            runs_per_query=runs_per_query,
+            trigger_threshold=trigger_threshold,
+            model=model,
+        )
+        eval_elapsed = time.time() - t0
+
+        # Split results back into train/test by matching queries
+        train_queries_set = {q["query"] for q in train_set}
+        train_result_list = [r for r in all_results["results"] if r["query"] in train_queries_set]
+        test_result_list = [r for r in all_results["results"] if r["query"] not in train_queries_set]
+
+        train_passed = sum(1 for r in train_result_list if r["pass"])
+        train_total = len(train_result_list)
+        train_summary = {"passed": train_passed, "failed": train_total - train_passed, "total": train_total}
+        train_results = {"results": train_result_list, "summary": train_summary}
+
+        if test_set:
+            test_passed = sum(1 for r in test_result_list if r["pass"])
+            test_total = len(test_result_list)
+            test_summary = {"passed": test_passed, "failed": test_total - test_passed, "total": test_total}
+            test_results = {"results": test_result_list, "summary": test_summary}
+        else:
+            test_results = None
+            test_summary = None
+
+        history.append({
+            "iteration": iteration,
+            "description": current_description,
+            "train_passed": train_summary["passed"],
+            "train_failed": train_summary["failed"],
+            "train_total": train_summary["total"],
+            "train_results": train_results["results"],
+            "test_passed": test_summary["passed"] if test_summary else None,
+            "test_failed": test_summary["failed"] if test_summary else None,
+            "test_total": test_summary["total"] if test_summary else None,
+            "test_results": test_results["results"] if test_results else None,
+            # For backward compat with report generator
+            "passed": train_summary["passed"],
+            "failed": train_summary["failed"],
+            "total": train_summary["total"],
+            "results": train_results["results"],
+        })
+
+        # Write live report if path provided
+        if live_report_path:
+            partial_output = {
+                "original_description": original_description,
+                "best_description": current_description,
+                "best_score": "in progress",
+                "iterations_run": len(history),
+                "holdout": holdout,
+                "train_size": len(train_set),
+                "test_size": len(test_set),
+                "history": history,
+            }
+            live_report_path.write_text(generate_html(partial_output, auto_refresh=True, skill_name=name))
+
+        if verbose:
+            def print_eval_stats(label, results, elapsed):
+                pos = [r for r in results if r["should_trigger"]]
+                neg = [r for r in results if not r["should_trigger"]]
+                tp = sum(r["triggers"] for r in pos)
+                pos_runs = sum(r["runs"] for r in pos)
+                fn = pos_runs - tp
+                fp = sum(r["triggers"] for r in neg)
+                neg_runs = sum(r["runs"] for r in neg)
+                tn = neg_runs - fp
+                total = tp + tn + fp + fn
+                precision = tp / (tp + fp) if (tp + fp) > 0 else 1.0
+                recall = tp / (tp + fn) if (tp + fn) > 0 else 1.0
+                accuracy = (tp + tn) / total if total > 0 else 0.0
+                print(f"{label}: {tp+tn}/{total} correct, precision={precision:.0%} recall={recall:.0%} accuracy={accuracy:.0%} ({elapsed:.1f}s)", file=sys.stderr)
+                for r in results:
+                    status = "PASS" if r["pass"] else "FAIL"
+                    rate_str = f"{r['triggers']}/{r['runs']}"
+                    print(f"  [{status}] rate={rate_str} expected={r['should_trigger']}: {r['query'][:60]}", file=sys.stderr)
+
+            print_eval_stats("Train", train_results["results"], eval_elapsed)
+            if test_summary:
+                print_eval_stats("Test ", test_results["results"], 0)
+
+        if train_summary["failed"] == 0:
+            exit_reason = f"all_passed (iteration {iteration})"
+            if verbose:
+                print(f"\nAll train queries passed on iteration {iteration}!", file=sys.stderr)
+            break
+
+        if iteration == max_iterations:
+            exit_reason = f"max_iterations ({max_iterations})"
+            if verbose:
+                print(f"\nMax iterations reached ({max_iterations}).", file=sys.stderr)
+            break
+
+        # Improve the description based on train results
+        if verbose:
+            print(f"\nImproving description...", file=sys.stderr)
+
+        t0 = time.time()
+        # Strip test scores from history so improvement model can't see them
+        blinded_history = [
+            {k: v for k, v in h.items() if not k.startswith("test_")}
+            for h in history
+        ]
+        new_description = improve_description(
+            skill_name=name,
+            skill_content=content,
+            current_description=current_description,
+            eval_results=train_results,
+            history=blinded_history,
+            model=model,
+            log_dir=log_dir,
+            iteration=iteration,
+        )
+        improve_elapsed = time.time() - t0
+
+        if verbose:
+            print(f"Proposed ({improve_elapsed:.1f}s): {new_description}", file=sys.stderr)
+
+        current_description = new_description
+
+    # Find the best iteration by TEST score (or train if no test set)
+    if test_set:
+        best = max(history, key=lambda h: h["test_passed"] or 0)
+        best_score = f"{best['test_passed']}/{best['test_total']}"
+    else:
+        best = max(history, key=lambda h: h["train_passed"])
+        best_score = f"{best['train_passed']}/{best['train_total']}"
+
+    if verbose:
+        print(f"\nExit reason: {exit_reason}", file=sys.stderr)
+        print(f"Best score: {best_score} (iteration {best['iteration']})", file=sys.stderr)
+
+    return {
+        "exit_reason": exit_reason,
+        "original_description": original_description,
+        "best_description": best["description"],
+        "best_score": best_score,
+        "best_train_score": f"{best['train_passed']}/{best['train_total']}",
+        "best_test_score": f"{best['test_passed']}/{best['test_total']}" if test_set else None,
+        "final_description": current_description,
+        "iterations_run": len(history),
+        "holdout": holdout,
+        "train_size": len(train_set),
+        "test_size": len(test_set),
+        "history": history,
+    }
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Run eval + improve loop")
+    parser.add_argument("--eval-set", required=True, help="Path to eval set JSON file")
+    parser.add_argument("--skill-path", required=True, help="Path to skill directory")
+    parser.add_argument("--description", default=None, help="Override starting description")
+    parser.add_argument("--num-workers", type=int, default=10, help="Number of parallel workers")
+    parser.add_argument("--timeout", type=int, default=30, help="Timeout per query in seconds")
+    parser.add_argument("--max-iterations", type=int, default=5, help="Max improvement iterations")
+    parser.add_argument("--runs-per-query", type=int, default=3, help="Number of runs per query")
+    parser.add_argument("--trigger-threshold", type=float, default=0.5, help="Trigger rate threshold")
+    parser.add_argument("--holdout", type=float, default=0.4, help="Fraction of eval set to hold out for testing (0 to disable)")
+    parser.add_argument("--model", required=True, help="Model for improvement")
+    parser.add_argument("--verbose", action="store_true", help="Print progress to stderr")
+    parser.add_argument("--report", default="auto", help="Generate HTML report at this path (default: 'auto' for temp file, 'none' to disable)")
+    parser.add_argument("--results-dir", default=None, help="Save all outputs (results.json, report.html, log.txt) to a timestamped subdirectory here")
+    args = parser.parse_args()
+
+    eval_set = json.loads(Path(args.eval_set).read_text())
+    skill_path = Path(args.skill_path)
+
+    if not (skill_path / "SKILL.md").exists():
+        print(f"Error: No SKILL.md found at {skill_path}", file=sys.stderr)
+        sys.exit(1)
+
+    name, _, _ = parse_skill_md(skill_path)
+
+    # Set up live report path
+    if args.report != "none":
+        if args.report == "auto":
+            timestamp = time.strftime("%Y%m%d_%H%M%S")
+            live_report_path = Path(tempfile.gettempdir()) / f"skill_description_report_{skill_path.name}_{timestamp}.html"
+        else:
+            live_report_path = Path(args.report)
+        # Open the report immediately so the user can watch
+        live_report_path.write_text("<html><body><h1>Starting optimization loop...</h1><meta http-equiv='refresh' content='5'></body></html>")
+        webbrowser.open(str(live_report_path))
+    else:
+        live_report_path = None
+
+    # Determine output directory (create before run_loop so logs can be written)
+    if args.results_dir:
+        timestamp = time.strftime("%Y-%m-%d_%H%M%S")
+        results_dir = Path(args.results_dir) / timestamp
+        results_dir.mkdir(parents=True, exist_ok=True)
+    else:
+        results_dir = None
+
+    log_dir = results_dir / "logs" if results_dir else None
+
+    output = run_loop(
+        eval_set=eval_set,
+        skill_path=skill_path,
+        description_override=args.description,
+        num_workers=args.num_workers,
+        timeout=args.timeout,
+        max_iterations=args.max_iterations,
+        runs_per_query=args.runs_per_query,
+        trigger_threshold=args.trigger_threshold,
+        holdout=args.holdout,
+        model=args.model,
+        verbose=args.verbose,
+        live_report_path=live_report_path,
+        log_dir=log_dir,
+    )
+
+    # Save JSON output
+    json_output = json.dumps(output, indent=2)
+    print(json_output)
+    if results_dir:
+        (results_dir / "results.json").write_text(json_output)
+
+    # Write final HTML report (without auto-refresh)
+    if live_report_path:
+        live_report_path.write_text(generate_html(output, auto_refresh=False, skill_name=name))
+        print(f"\nReport: {live_report_path}", file=sys.stderr)
+
+    if results_dir and live_report_path:
+        (results_dir / "report.html").write_text(generate_html(output, auto_refresh=False, skill_name=name))
+
+    if results_dir:
+        print(f"Results saved to: {results_dir}", file=sys.stderr)
+
+
+if __name__ == "__main__":
+    main()

package/.agents/skills/skill-creator/scripts/utils.py

@@ -0,0 +1,47 @@
+"""Shared utilities for skill-creator scripts."""
+
+from pathlib import Path
+
+
+
+def parse_skill_md(skill_path: Path) -> tuple[str, str, str]:
+    """Parse a SKILL.md file, returning (name, description, full_content)."""
+    content = (skill_path / "SKILL.md").read_text()
+    lines = content.split("\n")
+
+    if lines[0].strip() != "---":
+        raise ValueError("SKILL.md missing frontmatter (no opening ---)")
+
+    end_idx = None
+    for i, line in enumerate(lines[1:], start=1):
+        if line.strip() == "---":
+            end_idx = i
+            break
+
+    if end_idx is None:
+        raise ValueError("SKILL.md missing frontmatter (no closing ---)")
+
+    name = ""
+    description = ""
+    frontmatter_lines = lines[1:end_idx]
+    i = 0
+    while i < len(frontmatter_lines):
+        line = frontmatter_lines[i]
+        if line.startswith("name:"):
+            name = line[len("name:"):].strip().strip('"').strip("'")
+        elif line.startswith("description:"):
+            value = line[len("description:"):].strip()
+            # Handle YAML multiline indicators (>, |, >-, |-)
+            if value in (">", "|", ">-", "|-"):
+                continuation_lines: list[str] = []
+                i += 1
+                while i < len(frontmatter_lines) and (frontmatter_lines[i].startswith("  ") or frontmatter_lines[i].startswith("\t")):
+                    continuation_lines.append(frontmatter_lines[i].strip())
+                    i += 1
+                description = " ".join(continuation_lines)
+                continue
+            else:
+                description = value.strip('"').strip("'")
+        i += 1
+
+    return name, description, content

package/.agents/skills/tdd/SKILL.md

@@ -1,109 +1,36 @@
 ---
 name: tdd
-description: Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
+description: Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
 ---
 
 # Test-Driven Development
 
-## Philosophy
+TDD is the red → green loop. This skill is the reference that makes that loop produce tests worth keeping: what a good test is, where tests go, the anti-patterns, and the rules of the loop. Every section applies on every cycle — consult them before and during the loop, not after.
 
-**Core principle**: Tests should verify behavior through public interfaces, not implementation details. Code can change entirely; tests shouldn't.
+When exploring the codebase, read `CONTEXT.md` (if it exists) so test names and interface vocabulary match the project's domain language, and respect ADRs in the area you're touching.
 
-**Good tests** are integration-style: they exercise real code paths through public APIs. They describe _what_ the system does, not _how_ it does it. A good test reads like a specification - "user can checkout with valid cart" tells you exactly what capability exists. These tests survive refactors because they don't care about internal structure.
+## What a good test is
 
-**Bad tests** are coupled to implementation. They mock internal collaborators, test private methods, or verify through external means (like querying a database directly instead of using the interface). The warning sign: your test breaks when you refactor, but behavior hasn't changed. If you rename an internal function and tests fail, those tests were testing implementation, not behavior.
+Tests verify behavior through public interfaces, not implementation details. Code can change entirely; tests shouldn't. A good test reads like a specification — "user can checkout with valid cart" tells you exactly what capability exists — and survives refactors because it doesn't care about internal structure.
 
 See [tests.md](tests.md) for examples and [mocking.md](mocking.md) for mocking guidelines.
 
-## Anti-Pattern: Horizontal Slices
+## Seams — where tests go
 
-**DO NOT write all tests first, then all implementation.** This is "horizontal slicing" - treating RED as "write all tests" and GREEN as "write all code."
+A **seam** is the public boundary you test at: the interface where you observe behavior without reaching inside. Tests live at seams, never against internals.
 
-This produces **crap tests**:
+**Test only at pre-agreed seams.** Before writing any test, write down the seams under test and confirm them with the user. No test is written at an unconfirmed seam. You can't test everything — agreeing the seams up front is how testing effort lands on the critical paths and complex logic instead of every edge case.
 
-- Tests written in bulk test _imagined_ behavior, not _actual_ behavior
-- You end up testing the _shape_ of things (data structures, function signatures) rather than user-facing behavior
-- Tests become insensitive to real changes - they pass when behavior breaks, fail when behavior is fine
-- You outrun your headlights, committing to test structure before understanding the implementation
+Ask: "What's the public interface, and which seams should we test?"
 
-**Correct approach**: Vertical slices via tracer bullets. One test → one implementation → repeat. Each test responds to what you learned from the previous cycle. Because you just wrote the code, you know exactly what behavior matters and how to verify it.
+## Anti-patterns
 
-```
-WRONG (horizontal):
-  RED:   test1, test2, test3, test4, test5
-  GREEN: impl1, impl2, impl3, impl4, impl5
+- **Implementation-coupled** — mocks internal collaborators, tests private methods, or verifies through a side channel (querying the database instead of using the interface). The tell: the test breaks when you refactor but behavior hasn't changed.
+- **Tautological** — the assertion recomputes the expected value the way the code does (`expect(add(a, b)).toBe(a + b)`, a snapshot derived by hand the same way, a constant asserted equal to itself), so it passes by construction and can never disagree with the code. Expected values must come from an independent source of truth — a known-good literal, a worked example, the spec.
+- **Horizontal slicing** — writing all tests first, then all implementation. Bulk tests verify _imagined_ behavior: you test the _shape_ of things rather than user-facing behavior, the tests go insensitive to real changes, and you commit to test structure before understanding the implementation. Work in **vertical slices** instead — one test → one implementation → repeat, each test a **tracer bullet** that responds to what the last cycle taught you.
 
-RIGHT (vertical):
-  RED→GREEN: test1→impl1
-  RED→GREEN: test2→impl2
-  RED→GREEN: test3→impl3
-  ...
-```
+## Rules of the loop
 
-## Workflow
-
-### 1. Planning
-
-When exploring the codebase, use the project's domain glossary so that test names and interface vocabulary match the project's language, and respect ADRs in the area you're touching.
-
-Before writing any code:
-
-- [ ] Confirm with user what interface changes are needed
-- [ ] Confirm with user which behaviors to test (prioritize)
-- [ ] Identify opportunities for [deep modules](deep-modules.md) (small interface, deep implementation)
-- [ ] Design interfaces for [testability](interface-design.md)
-- [ ] List the behaviors to test (not implementation steps)
-- [ ] Get user approval on the plan
-
-Ask: "What should the public interface look like? Which behaviors are most important to test?"
-
-**You can't test everything.** Confirm with the user exactly which behaviors matter most. Focus testing effort on critical paths and complex logic, not every possible edge case.
-
-### 2. Tracer Bullet
-
-Write ONE test that confirms ONE thing about the system:
-
-```
-RED:   Write test for first behavior → test fails
-GREEN: Write minimal code to pass → test passes
-```
-
-This is your tracer bullet - proves the path works end-to-end.
-
-### 3. Incremental Loop
-
-For each remaining behavior:
-
-```
-RED:   Write next test → fails
-GREEN: Minimal code to pass → passes
-```
-
-Rules:
-
-- One test at a time
-- Only enough code to pass current test
-- Don't anticipate future tests
-- Keep tests focused on observable behavior
-
-### 4. Refactor
-
-After all tests pass, look for [refactor candidates](refactoring.md):
-
-- [ ] Extract duplication
-- [ ] Deepen modules (move complexity behind simple interfaces)
-- [ ] Apply SOLID principles where natural
-- [ ] Consider what new code reveals about existing code
-- [ ] Run tests after each refactor step
-
-**Never refactor while RED.** Get to GREEN first.
-
-## Checklist Per Cycle
-
-```
-[ ] Test describes behavior, not implementation
-[ ] Test uses public interface only
-[ ] Test would survive internal refactor
-[ ] Code is minimal for this test
-[ ] No speculative features added
-```
+- **Red before green.** Write the failing test first, then only enough code to pass it. Don't anticipate future tests or add speculative features.
+- **One slice at a time.** One seam, one test, one minimal implementation per cycle.
+- **Refactoring is not part of the loop.** It belongs to the review stage (see the `code-review` skill), not the red → green implementation cycle.

package/.agents/skills/tdd/tests.md

@@ -59,3 +59,19 @@ test("createUser makes user retrievable", async () => {
   expect(retrieved.name).toBe("Alice");
 });
 ```
+
+**Tautological tests**: Expected value restates the implementation, so the test passes by construction.
+
+```typescript
+// BAD: Expected value is recomputed the way the code computes it
+test("calculateTotal sums line items", () => {
+  const items = [{ price: 10 }, { price: 5 }];
+  const expected = items.reduce((sum, i) => sum + i.price, 0);
+  expect(calculateTotal(items)).toBe(expected);
+});
+
+// GOOD: Expected value is an independent, known literal
+test("calculateTotal sums line items", () => {
+  expect(calculateTotal([{ price: 10 }, { price: 5 }])).toBe(15);
+});
+```

package/.agents/skills/teach/GLOSSARY-FORMAT.md

@@ -0,0 +1,35 @@
+# GLOSSARY.md Format
+
+`GLOSSARY.md` is the canonical language for this teaching workspace. All explainers, exercises, and learning records should adhere to its terminology. Building it is itself part of learning: compressing a concept into a tight definition is evidence the user understands it.
+
+## Structure
+
+```md
+# {Topic} Glossary
+
+{One or two sentence description of the topic this glossary covers.}
+
+## Terms
+
+**Hypertrophy**:
+Muscle growth driven by mechanical tension and metabolic stress over repeated training sessions.
+_Avoid_: Bulking, getting big
+
+**Progressive overload**:
+Systematically increasing the demand on a muscle over time — via load, volume, or intensity.
+_Avoid_: Pushing harder, levelling up
+
+**RPE (Rate of Perceived Exertion)**:
+A 1–10 self-rating of how hard a set felt, where 10 is failure and 8 means two reps left in the tank.
+_Avoid_: Effort score, intensity rating
+```
+
+## Rules
+
+- **Add a term only when the user understands it.** The glossary is a record of compressed knowledge, not a dictionary the user reads to learn. If the user has just been introduced to a concept, wait until they can use it correctly before promoting it here.
+- **Be opinionated.** When several words exist for the same concept, pick the best one and list the rest as aliases to avoid. This is how language compresses.
+- **Keep definitions tight.** One or two sentences. Define what the term IS, not what it does or how to do it.
+- **Use the glossary's own terms inside definitions.** Once a term is in the glossary, prefer it everywhere — including inside other definitions. This is what makes complex terms easier to grasp later.
+- **Group under subheadings** when natural clusters emerge (e.g. `## Anatomy`, `## Programming`). A flat list is fine when terms cohere.
+- **Flag ambiguities explicitly.** If a term is used loosely in the wider field, note the resolution: "In this workspace, 'set' always means a working set — warm-ups are tracked separately."
+- **Revise as understanding deepens.** A definition the user wrote in week one may be wrong by week six. Update in place; do not leave stale entries.

package/.agents/skills/teach/LEARNING-RECORD-FORMAT.md

@@ -0,0 +1,46 @@
+# Learning Record Format
+
+Learning records live in `./learning-records/` and use sequential numbering: `0001-slug.md`, `0002-slug.md`, etc. Create the directory lazily — only when the first record is written.
+
+They are the teaching equivalent of ADRs: they capture non-obvious lessons, key insights, and stated prior knowledge that will steer future sessions. They are used to calculate the zone of proximal development.
+
+## Template
+
+```md
+# {Short title of what was learned or established}
+
+{1-3 sentences: what was learned (or what prior knowledge was established), and why it matters for future sessions.}
+```
+
+That is the whole format. A learning record can be a single paragraph. The value is recording _that_ this is now known and _why_ it changes what to teach next — not in filling out sections.
+
+## Optional sections
+
+Only include these when they add genuine value. Most records won't need them.
+
+- **Status** frontmatter (`active | superseded by LR-NNNN`) — useful when an earlier understanding turns out to be wrong and is replaced.
+- **Evidence** — how the user demonstrated the understanding (a question answered, an exercise completed, prior experience cited). Useful when the claim might be revisited.
+- **Implications** — what this unlocks or rules out for future sessions. Worth recording when non-obvious.
+
+## Numbering
+
+Scan `./learning-records/` for the highest existing number and increment by one.
+
+## When to write a learning record
+
+Write one when any of these is true:
+
+1. **The user demonstrated genuine understanding of something non-trivial** — not just exposure, but evidence they can use the concept correctly. This sets a new floor for what to teach next.
+2. **The user disclosed prior knowledge** — "I already know X." Record it so future sessions don't re-teach it. Also record the _depth_ claimed.
+3. **A misconception was corrected** — the user previously believed something wrong and now sees why. These are high-value: they predict future stumbling blocks for related topics.
+4. **The mission shifted in response to learning** — the user discovered they cared about something different than they thought. Cross-link to [[MISSION.md]] and update it.
+
+### What does _not_ qualify
+
+- Material that was merely covered. Coverage is not learning. Wait for evidence.
+- Anything already captured tersely in [[GLOSSARY.md]] as a term definition. Don't duplicate.
+- Session-by-session activity logs. Learning records are not a journal — they are decision-grade insights.
+
+## Supersession
+
+When a later record contradicts an earlier one (the user's understanding deepened or corrected), mark the old record `Status: superseded by LR-NNNN` rather than deleting it. The history of how understanding evolved is itself useful signal.

package/.agents/skills/teach/MISSION-FORMAT.md

@@ -0,0 +1,31 @@
+# MISSION.md Format
+
+`MISSION.md` lives at the workspace root. It captures the _reason_ the user is learning this topic. Every teaching decision — what to teach next, which resources to surface, which exercises to design — should trace back to this document.
+
+## Template
+
+```md
+# Mission: {Topic}
+
+## Why
+{1-3 sentences. The concrete real-world goal the user is chasing. What changes in their life or work when they have this skill? Avoid abstract framings like "to understand X" — push for the underlying outcome.}
+
+## Success looks like
+- {A specific, observable thing the user will be able to do}
+- {Another specific thing}
+- {…}
+
+## Constraints
+- {Time, budget, prior commitments, learning preferences, anything that bounds the approach}
+
+## Out of scope
+- {Adjacent topics the user explicitly does not want to chase right now — protects the zone of proximal development}
+```
+
+## Rules
+
+- **One mission per workspace.** If the user wants to learn two unrelated things, that is two workspaces.
+- **Concrete over abstract.** "Run a half marathon by October" beats "get fitter." "Ship a Rust CLI to my team" beats "learn Rust."
+- **Push back on vagueness.** If the user cannot articulate why, interview them before writing anything. A bad mission is worse than no mission.
+- **Revise when reality shifts.** Missions change. When the user's goal moves, update this file — don't leave a stale mission steering future sessions.
+- **Keep it short.** If `MISSION.md` runs past a screen, it has stopped being a compass and started being a plan.