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/chloride233/semantic-runtime/agents-mdgit clone --depth 1 https://github.com/Chloride233/semantic-runtimeWhat 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 | $0.00508 | $0.00508 |
| Opus 5 | $0.00254 | $0.00254 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
semantic-runtime 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 yesterday.
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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Runtime project rules
Purpose
Semantic Runtime is an open-source semantic infrastructure layer for AI Agents: it provides semantic understanding, context resolution, evidence, and safe execution between models and tools. It does not replace LLMs, agent frameworks, databases, or MCP.
Run and verify
- Install development dependencies:
python -m pip install -e '.[dev]'. - Run tests:
python -m pytest -q. - Run lint:
python -m ruff check src tests. - uv-managed alternative:
uv sync --extra devthenuv run pytest -q.
Stack and layout
- Python 3.12,
src/layout; runtime code lives insrc/semantic_runtime/. - Design specifications live in
docs/and are the source of truth; superseded v0.1 drafts are archived indocs/archive/. Semantic Runtime.mdat the repository root is the Obsidian index (MOC); wikilinks resolve by filename, so notes moved intodocs/stay intact.- Unit tests live in
tests/unit/; integration tests belong intests/integration/.
Current contract
- Core Phases 1-5 are shipped: data models (Entity / Relation / Metric /
Evidence / Policy), YAML model loader, registry, graph engine, deterministic
context resolver, metric dependency resolution, policy-based operation
validation, SQL guardrails, model integrity validation, MCP server
(
python -m semantic_runtime.mcp <model.yaml>, stdio and streamable HTTP), schema connectors (SQLite built-in; PostgreSQL/MySQL/Snowflake via optional extras), built-in domain packs (semantic_runtime.packs: ecommerce, saas, finance, game, healthcare), the SafetyProvider extension point, the v0.2 benchmark framework (benchmarks/runner.py, six question types, SRB score), and docker compose quick start. - Not yet shipped: JoinLint adapter, plugin system, third-party community packs, Snowflake-verified integration, and scripts tooling; do not claim them.
- New runtime behavior must come from the design documents in
docs/; behavior is not invented in code. Docs are updated when implementation clarifies or extends them (e.g. new error codes). - Keep README, rules, and docs aligned with implemented behavior.
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.
- yesterday First seen · 46 lines · 508 tokens per session scan A 8e18bef01c68
semantic-runtime AGENTS.md is an instructions file published in the GitHub repository Chloride233/semantic-runtime (0 stars, last pushed 1mo ago), licensed MIT. It adds 508 tokens to every session, about $0.0025 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 2026-09-01.
Other instructions, from other repositories
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
open-ontologies CLAUDE.md
Instructions for fabio-rovai/open-ontologies, covering open ontologies, ontology engineering workflow, generate, validate and load and reason.
engraphis CLAUDE.md
Instructions for Coding-Dev-Tools/engraphis, covering claude.md, the one rule that prevents most mistakes, before you say "done" — run the canonical gate, slash commands available here and working style in this repo.
kglite CLAUDE.md
Instructions for kkollsga/kglite, covering kglite — claude code conventions, build & test, architecture, the boundary principle (wrappers vs core) — summary and in-memory is the core product.
tpu_performance_autoresearch_wiki GEMINI.md
Instructions for vlasenkoalexey/tpu_performance_autoresearch_wiki, covering gemini/antigravity operating rules, platform adaptation (claude code → gemini/antigravity), 1. skills — native, no emulation, 2. never-stop hook & retrospectives and 3. session and transcript resolution.
tpu_performance_autoresearch_wiki AGENTS.md
Instructions for vlasenkoalexey/tpu_performance_autoresearch_wiki, covering codex instructions, compatibility, operating rules and codex translation notes.