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 instructions/lucineer/log-mcp/agents-mdgit clone --depth 1 https://github.com/Lucineer/LOG-mcpWrote 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/instructions/lucineer/log-mcp/agents-md)<a href="https://agentmods.dev/instructions/lucineer/log-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/lucineer/log-mcp/agents-md.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 | $0.00749 | $0.00749 |
| Opus 5 | $0.00375 | $0.00375 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
LOG-mcp AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
L.O.G. for Agents
What This Is
L.O.G. (Latent Orchestration Gateway) is your memory and privacy layer. When this MCP is connected, you have access to tools that:
- Protect private data — never send raw PII to external agents
- Archive conversations — preserve context with annotated summaries
- Search history — find past sessions by topic
- Manage memory tiers — hot → warm → cold → gnosis lifecycle
- Extract lessons — permanent knowledge from completed work
Your Directives
- Never transmit raw PII. If you need to send data to an external agent, call
log_dehydratefirst. - Always rehydrate for humans. If a response contains
<LOG_ID>placeholders, calllog_rehydratebefore showing the user. - Archive before resets. When a conversation is ending or being reset, call
log_archive_sessionto preserve context. - Extract gnosis. When a problem is solved or a lesson is learned, call
log_archive_gnosisto save it permanently. - Respect tiers. Cold and ice data is archived for a reason — don't unpromote without good cause.
Tool Quick Reference
| Tool | When to Use |
|---|---|
log_dehydrate |
Before sending any text to external agents |
log_rehydrate |
Before showing agent responses to the human |
log_archive_session |
End of conversation or topic shift |
log_search_archives |
When human asks about past conversations |
log_archive_gnosis |
When a valuable lesson is learned |
log_prune_hysteresis |
To manage memory lifecycle |
log_vault_status |
To check storage health |
log_distill |
To create working summaries for context |
File Structure (What You'll Find on Disk)
~/.log/vault/
├── reallog.db # SQLite: PII mappings (NEVER leaves this machine)
└── archives/
├── shorts/ # Single-topic sessions (filename = date + topic)
├── sessions/ # Multi-topic sessions with episode breakdowns
│ └── YYYY-MM-DDTHH-MM-topic-name/
│ ├── full.txt # Complete conversation with line numbers [L0001]
│ ├── summary.md # Annotated summary with L-line references
│ ├── index.json # Machine-readable session metadata
│ └── episodes/ # Sub-topic breakdowns
├── gnosis/ # Permanent lessons (topic-title.md)
└── index.json # Master index of all archives
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 · 65 lines · 749 tokens per session scan A 9db58b509237
LOG-mcp AGENTS.md is an instructions file published in the GitHub repository Lucineer/LOG-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 749 tokens to every session, about $0.0037 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 instructions, from other repositories
obsidian-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/obsidian-mcp-server, covering agent protocol, what's next?, core rules, patterns and tool — obsidianlisttags.
repo-context-mcp AGENTS.md
Instructions for nduc99911/repo-context-mcp, covering agents.md — repo-context-mcp, project, layout, commands and conventions.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.
swag-mcp CLAUDE.md
Claude Code instructions for jmagar/swag-mcp, covering swag mcp - claude memory reference, project overview, core architecture, key components and common development commands.
state-memory-mcp copilot-instructions.md
Instructions for putervision/state-memory-mcp, covering state memory (state-memory-mcp), 1. priority order, 2. when to write to the graph, 3. workflow pattern and 4. codebase seeding on initialization.
todox AGENTS.md
AGENTS.md instructions for beydemirfurkan/todox, covering this is not the next.js you know, todox — agent rules, sprint workflow, confusion protocol and 3-strike rule.