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 skills add Semiotronika/LINZA-MCP --skill linza-operatorgit clone --depth 1 https://github.com/Semiotronika/LINZA-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/skills/semiotronika/linza-mcp/linza-operator)<a href="https://agentmods.dev/skills/semiotronika/linza-mcp/linza-operator"><img src="https://agentmods.dev/badge/skills/semiotronika/linza-mcp/linza-operator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/semiotronika/linza-mcp/linza-operator"><img src="https://agentmods.dev/badge/skills/semiotronika/linza-mcp/linza-operator.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00061 | $0.01375 |
| Opus 5 | $0.00030 | $0.00687 |
| Sonnet 5 | $0.00012 | $0.00275 |
| Haiku 4.5 | $0.00006 | $0.00137 |
Grade A, and why
linza-operator 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 9d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LINZA Operator
Core Rule
Do not present LINZA as a flat MCP tool list. LINZA is a review-gated workflow:
load/index -> analyze -> review intents -> explicit apply -> context export
The user reviews meaning and approvals. The agent operates the tools.
Default Entry Points
Use these first:
agent_workspace(action="doctor")for readiness and safety status.guide_next_stepsfor the current onboarding/review stage.agent_workspacefor workspace maps, teaching, supervised growth, artifacts, trace review, memory search, review intents, graph connect, and context export.
When calling guide_next_steps, pass the user's language when known:
language="en" for English sessions and language="ru" for Russian sessions.
When the user asks "what is here", "where should we start", or "what should
the agent do next", use agent_workspace(action="map") first. Present the
user view, then use the agent view only to choose the next precise action.
When the user asks "what connects X and Y", use
agent_workspace(action="connect", source="X", target="Y") first. Present the
route and confidence labels, then read exact source files only if needed.
When the user wants the agent to learn the base style before continuing, use
agent_workspace(action="teach"). Show the small read-only seed batch and ask
the user to accept exact rq-* items that look right.
When showing agent_workspace(action="review_next"), present the readable
review-intent view from review_cards or human_view.cards. Treat raw
rq-* / aw-* IDs as apply handles, not as the main explanation.
When the user has accepted initial seed domains/material formats/hierarchy and
wants the agent to continue building the base, use
agent_workspace(action="grow", mode="assisted"). Keep the first batch dry-run,
show the selected items and selected_rules, then use dry_run=false only for
a small approved batch. This is supervised growth, not blind autopilot.
Use low-level tools only to support a clear workflow: indexing, search, explanation, review queue generation, and exact dry-run apply. Profiles, specialized reports, tag/property helpers, and legacy apply helpers are advanced tools, not the normal operator surface.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 153 lines · 61 tokens per session scan A 8c560185fcb5
linza-operator is a skill published in the GitHub repository Semiotronika/LINZA-MCP (4 stars, last pushed 27d ago), licensed MIT. It adds 61 tokens to every session and 1,375 once invoked, about $0.0003 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 skills, from other repositories
mneme-prime
Use when the user starts a new task that may have prior vault context worth surfacing. Invokes the mnemeprime MCP tool to build a token-budgeted preamble of recent sessions and topic matches.
mneme-search
Use when the user asks a factual question whose answer might live in the vault. Invokes mnemesearch. Production mnemesearch is FTS5 BM25. The experimental feature-hashed lexical-vector backend is not wired into MCP. KG enrichment is gated to summarize or timeline when full-profile graph state is active.
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
run-wenlan-app
Build, launch, screenshot, and drive the wenlan-app Tauri desktop app in dev mode on macOS (WKWebView) or Windows (WebView2). Use when asked to run or start the app, verify a UI change in the real running app (not just tests), or take a screenshot of it.
curate
Review pending Wenlan captures, revisions, or daemon refinements from Codex. Use for explicit audit walks after /brief or /handoff surfaces pending work. Invoked as /curate captures, /curate revisions, or /curate refinements.