tellur AGENTS.md

tellur AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from sydneyvb-nl/tellur. It costs 6,300 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Tellur, an AI code provenance platform that records how artificial intelligence took part in software changes. They explain the project layout, current status, development rules, and documentation sources.

In plain words
What is it for?
Orienting an agent before work, understanding Tellur's Rust core, command-line tool, editor plugins, dashboard, and packaging, and checking project status, workflows, adapters, and proposals.
Why use it?
They give coding agents a clear starting point and help them place changes in the correct part of a multi-component project. They also keep documentation aligned with the software's behavior and design.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: UserPromptSubmit hook event, but also the file is AGENTS.md. Also seen: mentions Claude Code; mentions Codex.

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/sydneyvb-nl/tellur/agents-md
Clone the repo
git clone --depth 1 https://github.com/sydneyvb-nl/tellur

Made for: Claude Code, 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 tellur AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sydneyvb-nl/tellur/agents-md.svg)](https://agentmods.dev/instructions/sydneyvb-nl/tellur/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sydneyvb-nl/tellur/agents-md"><img src="https://agentmods.dev/badge/instructions/sydneyvb-nl/tellur/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,300 This file is loaded in full into every session.
When invoked 6,300 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 5.1 $0.06300 $0.06300
Opus 5 $0.03150 $0.03150
Sonnet 5 $0.01260 $0.01260
Haiku 4.5 $0.00630 $0.00630

Measured 5d ago against content hash a292b1783519, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tellur 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.

AGENTS.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tellur Agent Instructions

These instructions apply to the whole repository.

Start Here (orientation for every run)

Tellur is an AI code provenance platform: Git tells you what changed, Tellur tells you how AI participated. Local-first, no cloud dependency. A Rust core + CLI (crates/), a VS Code extension and a JetBrains plugin (editor/), a static dashboard (web/), and packaging (dist/).

Read these in order before acting; they are the source of truth:

  1. PROJECT_STATUS.md — what is built, what is open, test counts, roadmap, blockers, and a dated changelog at the top. The single source of truth for status.
  2. This file's Architecture Map — where every layer lives, so you land changes in the right place.
  3. README.md — user-facing behavior: commands, setup, adapters, limits.
  4. docs/ADAPTERS.md — adapter mechanics, integration mechanisms (hooks vs extension vs MCP vs daemon webhook vs import), guarantees, and known limits.
  5. CONTRIBUTING.md — dev workflow and repo structure.
  6. docs/FINDINGS.md — historical review/remediation notes.
  7. docs/proposals/ — design proposals for not-yet-built features (e.g. TEAM_SERVER_MODE.md). Read before working on the matching roadmap item.

One-glance repository layout:

tellur/
├── crates/
│   ├── core/         # library: schema, storage, attribution, policy, redaction,
│   │                 #          export, daemon, mcp, notes, remap, report
│   ├── cli/          # the `tellur` binary (all commands + global setup)
│   ├── adapters/     # per-tool import parsers + hook/payload normalization
│   └── server/       # Tier 1 team hub (tellur-server) — FSL-1.1-ALv2, not Apache
│       └── ui/       #   embedded Svelte 5 dashboard SPA (built to ui/dist)
├── editor/
│   ├── tellur-vscode/    # VS Code / Cursor / Windsurf extension (TypeScript)
│   └── tellur-jetbrains/ # JetBrains IDE plugin (Kotlin/Gradle)
├── schemas/          # JSON Schema for session/event/attribution/pr-report/provenance
├── web/              # static session-replay dashboard (served by the daemon)
├── dist/             # npm wrapper + Homebrew formula
└── .github/workflows # CI + release automation

Read the full file on GitHub · 245 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. 5d ago First seen · 245 lines · 6,300 tokens per session scan A a292b1783519

Subscribe to this mod's changes

tellur AGENTS.md is an instructions file published in the GitHub repository sydneyvb-nl/tellur (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 6,300 tokens to every session, about $0.0315 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.