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 skills/dimetron/pi-go/memory-statusnpx skills add dimetron/pi-go --skill memory-statusgit clone --depth 1 https://github.com/dimetron/pi-goWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dimetron/pi-go/memory-status)<a href="https://agentmods.dev/skills/dimetron/pi-go/memory-status"><img src="https://agentmods.dev/badge/skills/dimetron/pi-go/memory-status.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00027 | $0.00499 |
| Opus 5 | $0.00014 | $0.00249 |
| Sonnet 5 | $0.00005 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
memory-status 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 4d 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.
What it actually says
When to use
Use this skill when the user wants to:
- Check the current state of the palace memory system
- See how many drawers, wings, and rooms exist
- Verify the embedding model is loaded
- View knowledge graph statistics (entities, triples, predicates)
- Diagnose palace issues or verify mining results
What it does
Runs pi memory status to display a comprehensive overview of the palace:
- Drawer count: Total knowledge units stored
- Wing count: Number of project namespaces
- Room count: Number of topical areas
- Model status: Whether the embedding model is loaded
- Knowledge Graph: Entity count, triple count (active vs total), predicates in use
- Wing details: Per-wing breakdown of drawers and rooms
Steps
- Run the status command:
# Default: looks for .pi-go/palace.db in current directory
pi memory status
# Specify a custom database path
pi memory status --db ~/.pi-go/palace.db
- If no palace database is found, suggest running
pi memory init . - Present the output to the user in a clear format
Arguments
The user can pass arguments after /memory-status:
--db <path>to specify a custom palace database path
Examples:
/memory-status— show status for current project/memory-status --db ~/.pi-go/palace.db— show status for global palace
Additional diagnostics
If the user needs deeper insight, chain with other commands:
# Search for specific knowledge
pi memory search "auth middleware"
# Check recent observations
pi memory recent
# View knowledge graph for an entity
pi memory kg query "pi-go"
# Show L0+L1 context that would be injected
pi memory wake-up
Notes
- If the palace DB doesn't exist, the command exits gracefully with instructions
- Model "not loaded" means semantic search falls back to FTS5 keyword matching
- Run
pi memory model downloadto enable semantic embeddings
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.
- 4d ago First seen · 80 lines · 27 tokens per session scan A ff6449fb3fe8
memory-status is a skill published in the GitHub repository dimetron/pi-go (151 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 499 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
use-modern-go
Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.
code-review-context
Codex maintains a context (history of messages) that is sent to the model in inference requests.
mcp-spec
Look up the normative MCP specification text for a method, field, header, or error code before implementing or changing it in fold. Use when a change touches wire behavior, when a reviewer asks "does the spec actually say that", or when answering a protocol question — never answer MCP protocol questions from memory.
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
jwx-companion-bulk
Apply bulk operations across all jwx companion modules. Args.
readme-generate
從原始碼分析自動生成雙語 README。當使用者請求為專案建立 README、需要從程式碼庫生成 README.md（英文）和 README.zh.md（中文）、或希望為其函式庫/套件建立一致的多語言文件時使用。.