ksor AGENTS.md

ksor AGENTS.md is an instructions file for Codex, OpenCode from panaversity/ksor. It costs 29,014 tokens per session, scanned A, original, Apache-2.0.

A set of repository rules for ksor, a command-line tool that turns governed Markdown files into a website for people and an MCP server for AI agents. MCP is a standard way for AI tools to discover and use external services.

In plain words
What is it for?
Use it when developing ksor, updating its Markdown processing or generated surfaces, maintaining bundled documentation, and checking that websites and MCP discovery files remain available.
Why use it?
It keeps citations, source tracking, refusal behavior, governance, pull-request workflow, and agent-discoverable documentation intact while the project changes.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/panaversity/ksor/agents-md
Clone the repo
git clone --depth 1 https://github.com/panaversity/ksor

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for ksor AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/panaversity/ksor/agents-md.svg)](https://agentmods.dev/instructions/panaversity/ksor/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/panaversity/ksor/agents-md"><img src="https://agentmods.dev/badge/instructions/panaversity/ksor/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 29,014 This file is loaded in full into every session.
When invoked 29,014 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.29014 $0.29014
Opus 5 $0.14507 $0.14507
Sonnet 5 $0.05803 $0.05803
Haiku 4.5 $0.02901 $0.02901

Measured today against content hash 9a225d859a31, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ksor 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.

AGENTS.md · 1,811 lines

How it starts

The opening of the file, as written. The whole thing — 1,811 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

The durable contract for working in this repository: what ksor is, the vocabulary, the decisions, the invariants, and how it is built and tested. Loaded every session, so it holds only what stays true — what is true this week lives in docs/status.md; the product pitch lives in README.md, its only home.

CLAUDE.md is a symlink to this file. They are the same file: one contract for every agent — human-readable and agent-readable, like everything else here.

Critical rules

  1. Never weaken provenance, citation, abstention, or governance guarantees to simplify an implementation. They are the product, not features of it.
  2. Never push directly to main. Every change lands through a pull request.
  3. Never break the agent-discoverable surfaces: docs bundled in the npm package (packages/ksor/docs/), and — once the site ships — its llms.txt and /.well-known/mcp/server.json. Agents finding ksor is how ksor gets used.

What this is, in one line

A CLI (ksor — the npm package is @panaversity/ksor) that compiles a folder of governed markdown into two surfaces — a static website for people and an MCP server for AI agents — with cited answers and honest abstention. It is not an agent framework; it is the knowledge layer agent frameworks read from.

Which verbs are implemented is not recorded here. This file describes what ksor is; docs/status.md holds what is built this week. One rule keeps the CLI itself the current answer: an unimplemented verb says so and exits 2, an unknown word is refused with exit 1 — so no document has to be kept in step with the binary.

A Python-era predecessor (vsor, panaversity/zia-vsor-sdk) proved much of the design. Its work may be taken and converted to TypeScript (decision 6), but it is a source to mine, not an authority to follow: nothing crosses without asking what it was for, and converted code re-earns its place with tests here.

What we claim, and to whom

Read the full file on GitHub · 1,811 lines

Changes

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.

  1. today Changed · +100 lines · +1,731 tokens per session 9a225d859a31
  2. 5d ago First seen · 1,711 lines · 27,283 tokens per session scan A 5c66392488b6

Subscribe to this mod's changes

ksor AGENTS.md is an instructions file published in the GitHub repository panaversity/ksor (145 stars, last pushed yesterday), licensed Apache-2.0. It adds 29,014 tokens to every session, about $0.1451 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.

Related

Other instructions, from other repositories

AI-Governance-Architecture CLAUDE.md

Claude Code instructions for war851/AI-Governance-Architecture, covering project: governed ai, stack: tbd — project-agnostic baseline, environment: windows 10 · powershell · cursor + claude code, architecture overview and application design.

war851/AI-Governance-Architecture · 985 tokens

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens