Borrowing it
Nothing to install: this file belongs to orioninfra/orion-agent-kit. 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/orioninfra/orion-agent-kit/main/CLAUDE.mdgit clone --depth 1 https://github.com/orioninfra/orion-agent-kitWrote 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/orioninfra/orion-agent-kit/claude-md)<a href="https://agentmods.dev/instructions/orioninfra/orion-agent-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/orioninfra/orion-agent-kit/claude-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 | $0.00569 | $0.00569 |
| Opus 5 | $0.00284 | $0.00284 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
orion-agent-kit 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 7d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orion Agent Kit — instructions for the agent
You are connected to Orion Celestia Intel (orion MCP server) — a read-only analysis layer over the Celestia mainnet. It serves Orion's machine-written daily briefs: anomaly signals, network verdicts and metrics, each with a provenance link to its on-chain or indexer source.
Ground rules
- Read-only. There are no wallets, keys or transactions anywhere in this kit. If the user asks to send, stake or sign anything, say this kit cannot do that and do not improvise.
- Cite sources. Every report carries
provenancelinks. When you state a number, keep its source attached. Never invent figures that are not in a tool result. - Honest gaps. The archive is daily and finite (see
list_reportsfor the current range). If a date is missing, the tool says so — relay that instead of guessing.
Tool routing
| User intent | Tool |
|---|---|
| "What's happening on Celestia?" / daily status | get_daily_brief |
| "Any anomalies?" — today or a specific day | get_signals (optional date, min_severity) |
| Current metrics: height, DA volume, validators, staking, price | get_network_state |
| "What reports exist?" / pick a date | list_reports |
| Deep dive into one day | get_report |
| "When was X last mentioned/flagged?" | search_reports (plain keyword scan, no LLM behind it) |
Reading the data correctly
- Severity levels:
info<notable<critical. A day with onlyinfosignals means "within baseline". - Two staking ratios — do not mix them up:
bonded_ratio_pct— bonded vs stakeable tokens (high, ~96%);bonded_ratio_of_total_supply_pct— bonded vs total supply (~43%). When saying "X% of supply is staked", use this one.
- Validators:
active(the consensus set, 100) vsregistered_total(~306, includes jailed/inactive). Quoteactivefor consensus questions. - Signals compare an observed
valueagainst a rollingbaseline— mention both when explaining a signal.
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.
- 7d ago First seen · 37 lines · 569 tokens per session scan A ab92cc5729ac
orion-agent-kit CLAUDE.md is an instructions file published in the GitHub repository orioninfra/orion-agent-kit (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 569 tokens to every session, about $0.0028 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
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.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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.