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/russellbrenner/jurisd/agents-mdgit clone --depth 1 https://github.com/russellbrenner/jurisdWrote 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/russellbrenner/jurisd/agents-md)<a href="https://agentmods.dev/instructions/russellbrenner/jurisd/agents-md"><img src="https://agentmods.dev/badge/instructions/russellbrenner/jurisd/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 5.1 | $0.00625 | $0.00625 |
| Opus 5 | $0.00313 | $0.00313 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
jurisd 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 5d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions for jurisd
Purpose
jurisd is a source-backed Australian legal research and provenance instrument over a governed command surface. It exposes legal research capabilities through MCP, CLI, and future TUI adapters.
Do not describe jurisd as a chatbot, oracle, AI companion, or autonomous legal advice system.
Current foundation architecture
Current files:
src/server.tsregisters the current MCP tool surface.src/cli.tshandles CLI entry before the server starts.
Foundation PR 1 is introducing planned command-surface governance files:
src/commands/types.tswill define command contract and authority metadata types.src/commands/contracts.tswill provide the command contract registry for CLI/docs/future adapters.docs/MCP-COMPATIBILITY.mdwill record the MCP compatibility set once present.
Command contract rule
Foundation PR 1 is introducing the command contract registry. Once present, add commands once through that registry.
Every public command contract needs:
- stable command id
- synopsis
- summary
- arguments
- flags
- stdin mode
- output modes
- exit codes
- validation schema reference or adapter mapping
- stability level
- side-effect class
- terminal safety policy
- capability gates
- result contract
Adapter-specific metadata is required when that adapter is enabled.
Until the registry exists, command surface changes must preserve MCP compatibility and update tests and docs together.
MCP surface rule
MCP tools are curated. Do not expose operator, install, update, destructive, filesystem-write, or network-write commands over MCP unless a later authority decision explicitly permits it.
Existing MCP tool names are compatibility-sensitive. Update docs/MCP-COMPATIBILITY.md once present. Before then, update the MCP tool-surface tests before changing the tool surface.
Security invariants
- No secrets in code, docs, logs, tests, command output, or examples.
- No shell execution with user-controlled strings.
- Treat CLI args, TUI input, MCP input, provider output, source text, filenames, URLs, and completion candidates as untrusted.
- Keep stdout for primary output and stderr for diagnostics.
- JSON and NDJSON output must not contain terminal decoration.
- Terminal output must strip or neutralise unsafe ANSI, OSC, control characters, and bidi controls when it renders untrusted text.
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.
- 5d ago First seen · 85 lines · 625 tokens per session scan A b34e14af280b
jurisd AGENTS.md is an instructions file published in the GitHub repository russellbrenner/jurisd (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 625 tokens to every session, about $0.0031 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 2026-08-30.
Other instructions, from other repositories
LightRAG AGENTS.md
AGENTS.md instructions for HKUDS/LightRAG, covering repository guidelines, project overview, project structure, module layout (lightrag/) and core architecture.
LightRAG CLAUDE.md
Claude Code instructions for HKUDS/LightRAG, a project described as:
graphify AGENTS.md
AGENTS.md instructions for Graphify-Labs/graphify: This project has a graphify knowledge graph at graphify-out/.
edgequake AGENTS.md
AGENTS.md instructions for raphaelmansuy/edgequake, covering repository guidelines, project structure & module organization, build, test, and development commands, quick start with make and start with ollama (default).
hugegraph-ai AGENTS.md
Instructions for apache/hugegraph-ai, covering agents.md, stack & modules, testing expectations, code search anchors and build & test.
ariadne AGENTS.md
AGENTS.md instructions for ajbarea/ariadne, covering agents.md — ariadne, what this project is, build & run, conventions and where things go.