Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/runtimenoteslabs/memory-layer/memory-contextgit clone --depth 1 https://github.com/runtimenoteslabs/memory-layerWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00008 | $0.00567 |
| Opus 5 | $0.00004 | $0.00283 |
| Sonnet 5 | $0.00002 | $0.00113 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
memory-context scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Context Command
Display the memories currently loaded in context for this project. This shows what the Memory Layer knows about your current working directory.
Usage
/memory-context [--detailed] [--category <cat>] [--limit N]
Options
| Option | Description | Default |
|---|---|---|
--detailed |
Show scores and metadata | false |
--category <cat> |
Filter by category | all |
--limit N |
Maximum memories to show | 20 |
--format <fmt> |
Output format (brief/detailed/structured) | brief |
Examples
# Show current context
/memory-context
# Show detailed view with scores
/memory-context --detailed
# Show only conventions
/memory-context --category convention
# Show all with structured format
/memory-context --format structured --limit 50
Implementation
Display project context:
mem context --project "$PWD" --format brief
Output Formats
Brief (default)
# Memory Context
- [architecture] Microservices with API gateway pattern
- [convention] Use snake_case for Python, camelCase for JS
- [gotcha] Auth service rate limits at 100 req/min
Detailed
# Memory Context (detailed)
## [abc123] ARCHITECTURE
Microservices with API gateway pattern
Score: 0.45 | Used: 12x | Confidence: 0.9
## [def456] CONVENTION
Use snake_case for Python, camelCase for JS
Score: 0.60 | Used: 8x | Confidence: 1.0
Structured
# Memory Context
## Architecture (2)
- [abc123] Microservices with API gateway pattern [proven]
- [def456] Event-driven communication between services
## Convention (3)
- [ghi789] Use snake_case for Python... [proven]
- [jkl012] Imports ordered: stdlib, third-party, local
When Context is Loaded
Memory context is automatically loaded:
- SessionStart: Top 10 relevant memories injected
- On demand: When Agent Skills detect relevant queries
- Explicitly: When you run
/memory-contextor/recall
Managing Context
- Memories with high outcome scores are prioritized
- Project-specific memories take precedence over global
- Recent memories get a slight boost
- Use
/outcometo improve future context relevance
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 99 lines · 8 tokens per session scan A a510494b2c00
memory-context is a command published in the GitHub repository runtimenoteslabs/memory-layer (10 stars, last pushed 3mo ago), licensed MIT. It adds 8 tokens to every session and 567 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
memory-status
Check the Pseudolife-MCP memory daemon and report bank health.
dream
Copy to .claude/commands/dream.md in any project to get /dream. -->.
tokenless-stats
Show Tokenless compression statistics.
evolve-lite-subscribe
Add a shared guidelines repo (read-scope subscription or write-scope publish target) to the unified repos list.
cb-search
코드브레인 BM25 검색 — stale 자동 refresh.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.