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>

.github/instructions/context7.instructions.md

@@ -0,0 +1,25 @@
+---
+applyTo: '**'
+description: Mandatory Context7 usage for external library, framework, SDK, API, CLI, and cloud-service work.
+---
+
+# Context7 Rules
+
+1. Use Context7 before using any external library, framework, SDK, API, CLI, or cloud service.
+2. Call `resolve-library-id` first.
+3. Call `query-docs` with the resolved id second.
+4. Base implementation on the returned docs.
+5. Cite the library id or doc source in notes when it affects decisions.
+6. Read the API key only from the `CONTEXT7_API_KEY` environment variable.
+7. Never write the API key to any file.
+8. Never put the API key in `.github/mcp.json`.
+9. Never paste the API key into prompts, logs, memory, or telemetry.
+10. If `CONTEXT7_API_KEY` is missing, stop library work.
+11. Tell the user exactly:
+
+```bash
+export CONTEXT7_API_KEY='<your-context7-api-key>'
+```
+
+12. Resume library work only after the environment variable exists.
+13. Continue non-library work when it does not depend on external docs.

.github/instructions/harness.instructions.md

@@ -0,0 +1,51 @@
+---
+applyTo: '**'
+description: Always-on lean harness behavior, token discipline, style, self-documenting rules, and scope guardrails.
+---
+
+# Lean Harness Rules
+
+## Token discipline
+
+1. Prefer `lh index --budget <N>` over raw tree reads.
+2. Prefer `lh graph --brief` over verbose diagnostics.
+3. Load only `.agents/memory/INDEX.md` by default.
+4. Pull memory shards only on demand with `lh memory get`.
+5. Return summaries, tables, and paths instead of file dumps.
+6. Keep skill bodies short. Use agents and `lh` commands for detail.
+
+## Imperative style
+
+1. Write commands as actions.
+2. Use short lines.
+3. Avoid motivational prose.
+4. Avoid generic LLM advice.
+5. State inputs, outputs, gates, and stop conditions.
+
+## Self-documenting work
+
+1. Write decisions to `.agents/specs/<slug>/decisions.md`.
+2. Write specs to `.agents/specs/<slug>/spec.md`.
+3. Write DAGs to `.agents/specs/<slug>/plan.dag.json`.
+4. Write run events to `.agents/runs/<id>/events.ndjson` through `lh run event`.
+5. Write journals to `.agents/runs/<id>/journal.md`.
+6. Keep ADRs inside `.agents/architecture.md`.
+7. Keep durable conventions in `.agents/conventions.md`.
+
+## Scope rule
+
+1. Respect lane scope globs exactly.
+2. Create write lanes with `lh lane create` before editing.
+3. Work inside the assigned worktree for write lanes.
+4. Never create files outside the lane scope.
+5. Stop and escalate when required scope is missing.
+6. Run `lh graph` before claiming done.
+
+## Pipeline rule
+
+1. Design before plan.
+2. Require user gate after design.
+3. Plan before build unless fast track applies.
+4. Run Ralph loop for every write lane.
+5. Merge lanes sequentially.
+6. Run one full verify after integration.

.github/instructions/memory.instructions.md

@@ -0,0 +1,37 @@
+---
+applyTo: '**'
+description: Rules for reading, writing, compacting, and protecting lean harness memory shards.
+---
+
+# Memory Rules
+
+## Read memory
+
+1. Load `.agents/memory/INDEX.md` by default.
+2. Do not load every shard at startup.
+3. Use `lh memory get --shard <name>` only when needed.
+4. Prefer compact shards over raw history.
+
+## Write memory
+
+1. Use `lh memory put --shard failures` for recurring failures and fixes.
+2. Use `lh memory put --shard corrections` for user corrections and changed assumptions.
+3. Use `lh memory put --shard insights` for reusable design or codebase facts.
+4. Use `lh memory put --shard conventions` for durable project rules.
+5. Use `lh memory put --shard quirks` for environment or tool behavior.
+6. Keep entries short, dated, and source-linked.
+7. Record what happened, why it matters, and where it applies.
+
+## Protect secrets
+
+1. Never write secrets to memory.
+2. Never write tokens, keys, passwords, cookies, private keys, or credentials.
+3. Run `lh memory scan` before saving risky content.
+4. Redact sensitive values at source.
+5. Stop and ask for remediation if a secret is already present.
+
+## Compact memory
+
+1. Use `lh memory compact` when shards grow noisy.
+2. Preserve decisions, fixes, conventions, and source paths.
+3. Drop duplicate logs and stale speculation.