Borrowing it
Nothing to install: this file belongs to teranos/ground. 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/teranos/ground/main/CLAUDE.mdgit clone --depth 1 https://github.com/teranos/groundWrote 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/teranos/ground/claude-md)<a href="https://agentmods.dev/instructions/teranos/ground/claude-md"><img src="https://agentmods.dev/badge/instructions/teranos/ground/claude-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/teranos/ground/claude-md"><img src="https://agentmods.dev/badge/instructions/teranos/ground/claude-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 | $0.00677 | $0.00677 |
| Opus 5.5 | $0.00271 | $0.00271 |
| Sonnet 5.5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
ground CLAUDE.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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New sessions should always read: README.md
OPERATIONAL DOC
Read the following files:
- source/hooks.d for control types, scope struct, and trigger builders.
- source/strop.d for value-shape validation on extracted flag values.
- source/sand/builtin.d for CTFE wiring — how pbt becomes static immutable scope arrays.
- source/controls.d and source/sand/load.d for the sand the engine holds — the built-in one, or a landed one whose ABI (source/sand/view.d) is the engine's.
- source/sand/text.d for what the controls compile from — the floor (an engine, -d-version=Floor) or everything wind gathered (make sand).
- source/nodeconfig.d for nodes.pbt, the node a ground speaks to when its controls name none.
- source/control_handlers.d for check, delay, and deliver handler implementations.
- source/immediate.d for immediate delivery — attestation format for external writers (QNTX, etc). A deferred message is an immediate row with an
aftergate. - source/sky.d for the courier that carries the immediate queue to its session.
- source/exec.d for exec dispatch — fork+pipe+wrapper, stdout/stderr capture, timeout.
- source/errors.d for the GroundError primitive and deliverError fallback chain (db → breadcrumb → stderr).
- source/pretooluse.d and source/stop.d for the two hook handlers everything above is wired into.
- source/git.d for git discovery — repo root and branch are file reads, check-ignore is libgit2; its one subprocess is
gh auth token, asked when the env holds no token and the store has no visibility for a GitHub origin. - grove/controls/*.pbt for the rituals — each carries its agent's
system:, so nothing else has to describe them.
Read UNDERGROUND.md for ug, the statusline, ug/*.d
The commands are the ground-commands skill, written by press from the modules that implement them.
TEST DRIVEN DEVELOPMENT (TDD)
RED: Write a failing test before implementing, Confirm it fails GREEN: Write code that makes the test pass. REFACTOR: Cohere with the rest of the codebase, finish the implementation fully.
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 Changed · +3 lines · +98 tokens per session 1359cd9d3981
- 15d ago Changed · -1 lines · -19 tokens per session 9640b2953371
- 28d ago Changed · +45 tokens per session 846bae29ea44
- 1mo ago Changed · +7 lines · +22 tokens per session f3791f7b33c3
- 1mo ago Changed · +10 lines · +13 tokens per session 48678f450cec
- 2mo ago First seen · 49 lines · 518 tokens per session scan A 6f18dce31665
ground CLAUDE.md is an instructions file published in the GitHub repository teranos/ground (4 stars, last pushed today), licensed MIT. It adds 677 tokens to every session, about $0.0027 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.
ground CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ground CLAUDE.mdteranos/ground | Instructions file | 4 | today | MIT | A | 677 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |