Borrowing it
Nothing to install: this file belongs to orbs-network/spot. 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/orbs-network/spot/master/AGENTS.mdgit clone --depth 1 https://github.com/orbs-network/spotWrote 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/orbs-network/spot/agents-md)<a href="https://agentmods.dev/instructions/orbs-network/spot/agents-md"><img src="https://agentmods.dev/badge/instructions/orbs-network/spot/agents-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/orbs-network/spot/agents-md"><img src="https://agentmods.dev/badge/instructions/orbs-network/spot/agents-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 | $0.02496 | $0.02496 |
| Opus 5.5 | $0.00998 | $0.00998 |
| Sonnet 5.5 | $0.00499 | $0.00499 |
| Haiku 4.5 | $0.00250 | $0.00250 |
Grade A, and why
spot 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project AGENTS.md
Scope
These instructions apply to the whole repository.
- Never open an issue on the Spot repository unless the user specifically asks for one.
- When adding a DEX integration, always use the universal adapter type unless the user explicitly specifies another type.
- Supported chains must be explicitly included in config and have all six core contracts plus at least one deployed shared or chain-specific adapter. Keep config and the skill chain list in sync; named solver count is not a prerequisite. Do not restore intentionally removed chains based on existing deployments; Manta is excluded.
Canonical Surfaces
The self-contained skill/ package is the canonical AI-agent bundle.
Within that bundle:
skill/SKILL.mdis the human and agent entrypoint and carries the inline machine-readable skill metadata.skill/SKILL.mdand the bundled markdown references are the canonical execution surface for the published skill.
Keep the canonical skill slug stable as spot-advanced-swap-orders.
Use Spot Advanced Swap Orders as the human-facing display title for the skill and hosted distribution surfaces.
The repository README.md is the exception and may use broader protocol-level branding. Keep it focused on protocol users and integrators; development, deployment, testing, and QA instructions belong only in AGENTS.md.
Keep skill/SKILL.md and config.json as the sync inputs for the inline metadata consumed by the self-contained skill package.
Optimize retrieval with frontmatter description and opening text before changing the skill slug again.
Sync Rules
When changing behavior, docs, packaging, or metadata that affects agent consumption, update all affected surfaces in the same change.
This commonly includes skill/SKILL.md, config.json, skill/, README.md, index.html, package.json, and derived metadata.
The canonical skill npm package name is @orbs-network/spot-skill.
Spot Runtime QA
Live relay coverage is a manual AI check during qa, or when explicitly requested. Normal testing (t, npm test, and test:e2e) checks contracts, deployments, and oracle coverage; it must not query service health or require runtime integration coverage. Do not query taker health endpoints during qa.
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 · -8 tokens per session 95d83ab65052
- 18d ago Changed · -1 lines · -97 tokens per session 9ae06a19a04c
- 29d ago Changed · +2 tokens per session 246c611d82ea
- 1mo ago Changed · +5 tokens per session 5a752f431cae
- 1mo ago Changed · +63 tokens per session 5992e35a76ad
- 1mo ago Changed · +35 tokens per session 0e4ebf183332
- 1mo ago Changed · +42 lines · +582 tokens per session 79bd96bb7b56
- 1mo ago Changed · +19 lines · +557 tokens per session 5f12464fd877
- 1mo ago Changed · +3 lines · +199 tokens per session 2dee30945cf5
- 1mo ago First seen · 78 lines · 1,158 tokens per session scan A e268aa2e375c
spot AGENTS.md is an instructions file published in the GitHub repository orbs-network/spot (2 stars, last pushed 5d ago), licensed MIT. It adds 2,496 tokens to every session, about $0.0100 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.
spot AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| spot AGENTS.mdorbs-network/spot | Instructions file | 2 | 5d ago | MIT | A | 2,496 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | 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 | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |