Borrowing it
Nothing to install: this file belongs to Knuckles-Team/epistemic-graph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Knuckles-Team/epistemic-graph/main/AGENTS.mdgit clone --depth 1 https://github.com/Knuckles-Team/epistemic-graphWrote 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/knuckles-team/epistemic-graph/agents-md)<a href="https://agentmods.dev/instructions/knuckles-team/epistemic-graph/agents-md"><img src="https://agentmods.dev/badge/instructions/knuckles-team/epistemic-graph/agents-md/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/instructions/knuckles-team/epistemic-graph/agents-md"><img src="https://agentmods.dev/badge/instructions/knuckles-team/epistemic-graph/agents-md.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 | $0.01554 | $0.01554 |
| Opus 5.5 | $0.00622 | $0.00622 |
| Sonnet 5.5 | $0.00311 | $0.00311 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
epistemic-graph 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 today.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
epistemic-graph
Agent contract
Tool-neutral rules for any AI agent or human working in this repository. This block is maintained by the fleet standard; edit outside the markers.
- Owner boundary: this repository owns facts, records, storage, query, retrieval, ingest, reasoning, decisions and choices. It is the native Rust engine (spec prefix
EG-). Query covers UQL and natural language. Feature routing across repositories: ecosystem boundaries. - Setup: run
scripts/bootstrap.sh. It is idempotent and non-interactive. It pins uv and Python, syncs the locked environment and installs the git hooks. It then prints the gate command. - Gates:
uvx pre-commit run --all-filesmust pass before any push. Never bypass hooks to get green. - Commits: one logical change per commit with a
Spec: <ID>trailer (orSpec: none (<reason>)), plus aCo-Authored-By:trailer naming the assisting agent. Stage explicit paths only; nevergit add -Aorgit add .. Commit under the author's configured Git identity, never a tool or bot name. - Org rules: organization AGENTS.md.
epistemic-graph is a standalone Rust database and compute engine for connected
knowledge, evidence, and multimodal data. Applications can use it directly; it
can also serve as the storage and reasoning engine beneath agent-utilities.
Agent orchestration, connectors, and governed ingestion belong to that optional
application layer, not to this database.
Boundaries
- Owns: facts, records, vocabulary, durable state and storage. It also owns query (UQL and natural language), retrieval, ingest, reasoning, decisions and choices. Code is native Rust, and each spec row sets budgets and names a benchmark.
- Never builds: served operations, admission or auth (route them to arbora). Connector contracts and transports go to agent-connector-sdk. Run mechanics go to agent-utilities.
- Allowed dependencies: Rust crates, and its own Python client and bindings. It imports no other ecosystem package.
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.
- today Changed · +12 lines · +299 tokens per session 165622145f27
- 5d ago Changed · +8 lines · +165 tokens per session 687df77ea630
- 11d ago Changed · +4 lines · +153 tokens per session 36191a462fba
- 23d ago Changed · -1 lines · -12 tokens per session c32181836164
- 24d ago Changed · +19 lines · +234 tokens per session c6fcbe6efbd2
- 1mo ago Changed · -1,066 lines · -27,638 tokens per session 853d1e365a58
- 1mo ago Changed · +12 tokens per session f9ec6f2820cc
- 1mo ago Changed · +158 lines · +2,672 tokens per session 63ce72a87b29
- 1mo ago First seen · 993 lines · 25,669 tokens per session scan A eb366915aab7
epistemic-graph AGENTS.md is an instructions file published in the GitHub repository Knuckles-Team/epistemic-graph (11 stars, last pushed today), licensed MIT. It adds 1,554 tokens to every session, about $0.0062 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.