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/tanya-ok/engineering-os/agents-mdgit clone --depth 1 https://github.com/tanya-ok/engineering-osWrote 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/tanya-ok/engineering-os/agents-md)<a href="https://agentmods.dev/instructions/tanya-ok/engineering-os/agents-md"><img src="https://agentmods.dev/badge/instructions/tanya-ok/engineering-os/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 | $0.00655 | $0.00655 |
| Opus 5 | $0.00328 | $0.00328 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
engineering-os 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS - Operational Policy
Rules for any AI agent (Claude Code, local LLMs, MCP clients) working in this
repo or in a vault created from vault-template/.
The contract: unified reading, segregated writing
- Reading: all three vaults (work, ai, user) are indexed together. Query
the RAG server (
POST :8765/search) for grounded context instead of guessing. - Writing: routed by content type per
rag/routing.json.- Your own identity, interaction rules, and observations about the collaboration go to the ai vault.
- Durable facts about the user are staged in the user vault
_inbox/, never written directly into its curated namespaces. - Operational work goes to the work vault domain it belongs to (CloudOps, FinOps, DevOps, SecOps, Architecture, Weekly).
- When unsure, default to the work vault and tag the note
needs-routing.
Standing behavioral, git, language, and security policies live in
standards/canonical/. Read them; they govern how you act here.
Boundaries
Always
- Write vault files atomically (temp file + rename); never truncate in place.
- Keep
_Index/Active Context.mdand_Index/Open Loops.mdcurrent when work state changes; they are the session-start context for every agent. - New architecture decisions go to
Architecture/decisions/using the ADR template, numbered sequentially. - English only in all committed artifacts.
Ask first
- Changing the vault folder structure or index schema.
- Adding dependencies.
Never
- Hardcode personal paths; every path comes from config or env.
- Commit secrets, tokens, or anything matching the anonymization gate
(
scripts/anonymization-check.shruns on pre-commit and pre-push). - Rewrite
rag/build_index.pychunking logic without regenerating the index.
Key files
| File | Role |
|---|---|
vault-template/ |
Work vault: five domains + _Index/ + Weekly/ |
ai-vault-template/ |
AI vault: identity, interaction rules, observations |
user-vault-template/ |
User vault: communication, environment, facts, _inbox/ |
rag/ |
TypeScript RAG layer: eos-rag CLI (index + serve), transformers.js + sqlite-vec |
rag/src/ |
indexer, search server (/health, /search hybrid + MMR), config, chunker |
rag/vaults.example.json |
Vault registry template (env-driven paths) |
rag/routing.example.json |
Write-routing contract (unified read, segregated write) |
standards/ |
Governance layer: canonical policies, skills, hooks, plugin manifest |
scripts/anonymization-check.sh |
Leak gate: generic patterns + optional local list |
scripts/setup.sh |
One-command bootstrap for a fresh clone |
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 · 57 lines · 655 tokens per session scan A 4fefbe358d33
engineering-os AGENTS.md is an instructions file published in the GitHub repository tanya-ok/engineering-os (2 stars, last pushed 11d ago), licensed MIT. It adds 655 tokens to every session, about $0.0033 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
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
obsidian-wiki AGENTS.md
AGENTS.md instructions for Ar9av/obsidian-wiki, covering obsidian wiki — agent context, readme translation parity, configuration, targeting a specific vault and vault structure.
llm-wiki-compiler AGENTS.md
AGENTS.md instructions for atomicstrata/llm-wiki-compiler, covering llmwiki, development guidelines, code style & standards, clean code rules and comments and documentation.
Starcat AGENTS.md
AGENTS.md instructions for starcat-app/Starcat, covering agents.md, 🚨 硬性铁律（每次写代码前必读，违反即返工）, 🌿 git 分支与 worktree（强制）, 🧭 主进度索引（每次开工前必读） and 状态符号（与功能实现总览.md 同步）.
Vault-Agent-Memory AGENTS.md
Instructions for zycaskevin/Vault-Agent-Memory, covering agent instructions for vault agent memory, common install architecture, second decision: optional features, first decision: database scope and safe agent workflow.
my-wiki AGENTS.md
Instructions for NimaChu/my-wiki, covering my wiki agent project, project map, knowledge model, route requests and development checks.