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 TIKAZI/TIKAZ-AI-Skills --skill context-onpremisegit clone --depth 1 https://github.com/TIKAZI/TIKAZ-AI-SkillsWrote 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/tikazi/tikaz-ai-skills/context-onpremise)<a href="https://agentmods.dev/skills/tikazi/tikaz-ai-skills/context-onpremise"><img src="https://agentmods.dev/badge/skills/tikazi/tikaz-ai-skills/context-onpremise/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/tikazi/tikaz-ai-skills/context-onpremise"><img src="https://agentmods.dev/badge/skills/tikazi/tikaz-ai-skills/context-onpremise.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 | $0.00047 | $0.00587 |
| Opus 5 | $0.00023 | $0.00293 |
| Sonnet 5 | $0.00009 | $0.00117 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
context-onpremise 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- context-onpremise — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TIKAZ Context On-Premise
Designed, integrated, independently refactored, and continuously maintained by TIKAZ.
Core promise
Find the right evidence before deciding whether to compress. Use local dependencies for complex documents, multimodal material, and semantic retrieval while keeping sources, facts, anchors, privacy, failures, and cost measurable.
Workflow
- Fix the task, required evidence slots, risk, text budget, and visual budget.
- Profile the input once and invoke only the necessary local route: document conversion, webpage extraction, media understanding, local retrieval/compression, or safe structured parsing.
- Protect numbers, versions, URLs, commands, errors, citations, table cells, approvals, and source anchors.
- Combine lexical evidence slots, BGE-M3, local reranking, and diversity-aware selection. Query expansions are retrieval hints, never source facts.
- Use LLMLingua-2 only for over-budget, low-risk natural-language prose. Never send protected blocks, code, commands, contracts, finance, tables, or security evidence to learned compression.
- Fall back visibly to deterministic selection or the original source when local models fail, evidence coverage is low, protected facts drop, or the budget conflicts with safety.
Output contract
Return canonical Markdown or a safe structured result, Context Pack, evidence ledger, retrieval ledger, cost ledger, omissions, and Pending items. Report Recall@K, Precision@K, MRR, nDCG@K, evidence-slot coverage, protected-fact recall, estimated tokens, latency, and fallback state separately. Without relevance labels, do not invent hit-rate percentages.
Validation and fallback
Validate protected literals, source anchors, required evidence slots, hard budget, adapter identity, and unresolved visual/table evidence before accepting the pack. If any required gate fails, return deterministic selection or the original source with the reason instead of claiming successful compression.
Installation
What ships with it
1 file 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.
- 8d ago First seen · 44 lines · 47 tokens per session scan A 95260413abac
context-onpremise is a skill published in the GitHub repository TIKAZI/TIKAZ-AI-Skills (6 stars, last pushed 9d ago), licensed MIT. It adds 47 tokens to every session and 587 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
fetch-llm-papers
Workflow for updating the LLM landscape paper pool (section/xllmpapers.md) using fetchllmpapers.py. Covers full re-fetch, resume from checkpoint, and adding new topics. USE FOR: Refreshing citation counts, expanding topic coverage. DO NOT USE FOR: Adding hand-curated entries to section files (use…
fetch-llm-apps
Workflow for updating the popular LLM applications pool (section/xllmapps.md) using fetchllmapps.py. Covers full refresh, alternate exports, topic tuning, and common pitfalls. USE FOR: Refreshing the ranked GitHub applications list linked from applications.md. DO NOT USE FOR: Hand-curating application entries inside…
convex-agents
Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration.
agent-v3-memory-specialist
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…