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>
38 lines
1.3 KiB
Markdown
38 lines
1.3 KiB
Markdown
---
|
|
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.
|