feat: scaffold redsen-lean-harness v0.1.0

Recovered from crashed session (Node OOM). Repo contains full P0-P6
scaffold: plugin.json/marketplace.json, AGENTS.md, ADRs 0001-0006,
lh CLI (init/index/graph/lane/run/memory/host/report/doctor), 10
.github/agents, 12 CLI skills, instructions, context7 mcp.json, and
unit/e2e test suite.

Fixed: run.mjs read --in-tokens/--out-tokens but tests and CLI docs
use --input-tokens/--output-tokens, so telemetry totals were always 0.
Now accepts both forms.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

templates/adr.md

@@ -0,0 +1,23 @@
+# ADR {{ID}}: {{TITLE}}
+
+## Status
+
+Proposed
+
+## Context
+
+What forces, constraints, and facts drive this decision?
+
+## Decision
+
+What option is chosen?
+
+## Consequences
+
+- Positive:
+- Negative:
+- Follow-up:
+
+## Alternatives considered
+
+- Option: why not.

templates/architecture.md

@@ -0,0 +1,30 @@
+# {{PROJECT}} architecture
+
+<!-- Living document. Update when components, data flow, invariants, or ADR outcomes change. Keep claims concrete and current. -->
+
+## Purpose
+
+Describe what this system exists to do, who uses it, and what success means.
+
+## System context
+
+List upstream callers, downstream services, data stores, queues, files, and trust boundaries.
+
+## Components
+
+- Component: responsibility, owner, key files.
+
+## Data flow
+
+1. Input source.
+2. Validation and transformation.
+3. Persistence or external calls.
+4. Output and observability.
+
+## Key invariants
+
+- Invariant: why it must hold, where enforced, how verified.
+
+## Decision log (ADRs)
+
+<!-- Append ADR links or summaries here. Newest last. -->

templates/conventions.md

@@ -0,0 +1,38 @@
+# {{PROJECT}} conventions
+
+<!-- Living document. Promote repeated review feedback and user corrections here. Keep rules specific, checkable, and current. -->
+
+## Code style
+
+- Prefer simple control flow and explicit names.
+- Keep side effects at boundaries.
+
+## Naming
+
+- Use domain terms consistently.
+- Name files after their primary responsibility.
+
+## Testing
+
+- Cover changed behaviour with the smallest meaningful test.
+- Add regression tests for fixed bugs.
+
+## Error handling
+
+- Fail fast on invalid inputs.
+- Preserve actionable error context without leaking secrets.
+
+## Commit format
+
+- Use concise conventional commits when possible.
+- Explain why in the body when not obvious.
+
+## Directory layout
+
+- Keep generated artifacts out of source directories.
+- Put shared deterministic helpers in library modules.
+
+## Review rules
+
+- Verify scoped files only.
+- Flag correctness, security, and contract drift before style.

templates/journal.md

@@ -0,0 +1,42 @@
+# Run journal: {{RUN_ID}}
+
+## Objective
+
+{{OBJECTIVE}}
+
+## Plan
+
+- Step:
+
+## Lanes
+
+| lane | role | scope | status |
+| --- | --- | --- | --- |
+
+## Files touched
+
+- path: reason
+
+## Commands run
+
+| command | result |
+| --- | --- |
+
+## Tokens
+
+- input:
+- output:
+- cache:
+
+## Wall time
+
+- started:
+- ended:
+
+## Outcome
+
+- Result:
+
+## Follow-ups
+
+- Item:

templates/memory-index.md

@@ -0,0 +1,10 @@
+# Memory index
+
+Only this file is always loaded. Open shard files only when needed.
+
+updated: {{UPDATED}}
+total_tokens: {{TOTAL_TOKENS}}
+
+| shard | entries | tokens | updated | summary |
+| --- | ---: | ---: | --- | --- |
+{{SHARDS}}

templates/memory-shard.md

@@ -0,0 +1,9 @@
+# {{SHARD}} memory
+
+{{DESCRIPTION}}
+
+Entries use:
+
+`## <ISO timestamp> — <title>`
+
+Optional next line: `tags: a, b`

templates/questionnaire.md

@@ -0,0 +1,67 @@
+# Design questionnaire: {{TITLE}}
+
+Edit answers in place, keep one numbered answer per question, then say "go". Recommended answers are marked.
+
+## 1. Primary goal?
+
+1. **Recommended:** Implement smallest complete behaviour that satisfies acceptance criteria.
+2. Explore architecture only; no code changes.
+3. Prototype disposable spike.
+
+Answer: 1
+
+## 2. Risk tolerance?
+
+1. **Recommended:** Conservative; preserve existing contracts and APIs.
+2. Moderate; allow internal refactors when verified.
+3. Aggressive; redesign if simpler.
+
+Answer: 1
+
+## 3. Compatibility target?
+
+1. **Recommended:** Backward compatible unless requirement says otherwise.
+2. Breaking changes allowed with migration notes.
+3. New surface only; no compatibility promise.
+
+Answer: 1
+
+## 4. Verification depth?
+
+1. **Recommended:** Run targeted tests plus configured verify commands that cover changed behaviour.
+2. Run targeted tests only.
+3. Full suite required before completion.
+
+Answer: 1
+
+## 5. Documentation updates?
+
+1. **Recommended:** Update docs directly tied to changed behaviour.
+2. No docs unless tests require them.
+3. Full architecture/conventions refresh.
+
+Answer: 1
+
+## 6. Parallelism?
+
+1. **Recommended:** Use read-only fan-out for independent research; serialize writes by scope.
+2. Single-lane implementation.
+3. Maximize lanes even for moderate coupling.
+
+Answer: 1
+
+## 7. External services?
+
+1. **Recommended:** Avoid new external calls unless existing workflow requires them.
+2. Use documented services when helpful.
+3. Ask user before any external call.
+
+Answer: 1
+
+## 8. Secret handling?
+
+1. **Recommended:** Never write secrets; require env vars or existing secret stores.
+2. Allow local uncommitted secret files.
+3. Inline placeholders only.
+
+Answer: 1

templates/spec.md

@@ -0,0 +1,32 @@
+# Spec: {{TITLE}}
+
+## Problem
+
+What user or system problem must be solved?
+
+## Scope
+
+### In
+
+- Included behaviour.
+
+### Out
+
+- Explicit non-goals.
+
+## Acceptance criteria
+
+1. Checkable outcome.
+2. Checkable outcome.
+
+## Constraints
+
+- Technical, product, security, timing, or compatibility constraints.
+
+## Risks
+
+- Risk: mitigation.
+
+## Verification plan
+
+- Command or manual check: expected result.