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/sydneyvb-nl/tellur/agents-mdgit clone --depth 1 https://github.com/sydneyvb-nl/tellurWrote 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/sydneyvb-nl/tellur/agents-md)<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>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 | $0.06300 | $0.06300 |
| Opus 5 | $0.03150 | $0.03150 |
| Sonnet 5 | $0.01260 | $0.01260 |
| Haiku 4.5 | $0.00630 | $0.00630 |
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.
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:
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.- This file's Architecture Map — where every layer lives, so you land changes in the right place.
README.md— user-facing behavior: commands, setup, adapters, limits.docs/ADAPTERS.md— adapter mechanics, integration mechanisms (hooks vs extension vs MCP vs daemon webhook vs import), guarantees, and known limits.CONTRIBUTING.md— dev workflow and repo structure.docs/FINDINGS.md— historical review/remediation notes.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
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 · 245 lines · 6,300 tokens per session scan A a292b1783519
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.
Other instructions, from other repositories
crystal CLAUDE.md
Instructions for stravu/crystal, covering crystal - multi-session claude code manager, project overview, references, implementation status: ✅ complete and ✅ implemented features.
easy-cheese python.instructions.md
Instructions for paulnsorensen/easy-cheese, covering hard rules, what to flag and what not to flag.
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
AmbyKit CLAUDE.md
Claude Code instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.