Borrowing it
Nothing to install: this file belongs to togethercomputer/skills. 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/togethercomputer/skills/main/AGENTS.mdgit clone --depth 1 https://github.com/togethercomputer/skillsWrote 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/togethercomputer/skills/agents-md)<a href="https://agentmods.dev/instructions/togethercomputer/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/togethercomputer/skills/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/togethercomputer/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/togethercomputer/skills/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 | $0.03706 | $0.03706 |
| Opus 5.5 | $0.01482 | $0.01482 |
| Sonnet 5.5 | $0.00741 | $0.00741 |
| Haiku 4.5 | $0.00371 | $0.00371 |
Grade A, and why
skills 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 9d 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository contains a single agent skill, together-ai, covering the whole Together AI
platform. It follows the Agent Skills specification and is
organised around progressive disclosure: triggering the skill costs a small, constant amount of
context no matter how many product areas it covers.
Architecture
Four levels. Each is opened only when the level above it says to.
| Level | What | Loaded when |
|---|---|---|
| 1 | SKILL.md frontmatter description |
always in context |
| 2 | SKILL.md body — the router |
the skill triggers |
| 3 | domains/AREA.md — one guide per product area |
the router points there |
| 4 | references/AREA/*.md, scripts/AREA/* |
a domain guide points there |
Every level is sized so an agent can decide what to load next without loading it first. The router
is small (about 70 lines) because every task pays for it: it holds setup, a one-line-per-area guide
table, and the rules that apply everywhere, and nothing product-specific. Each guide covers its
common path on its own and ends with an ## Open next menu stating every file's size, contents,
and when to open it, so agents skip files they do not need.
This shape comes from a measured regression. An earlier router was about 14k characters and told agents to read guides "fully" and to prefer scripts over memory; across 13 evaluated tasks, runs loaded 57% more skill content than with the separate per-product skills, at the same pass rate. Keep the router lean and the menus precise.
Domain registry
There are 15 domain guides under skills/together-ai/domains/:
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.
- 9d ago Changed · -1 lines · -7 tokens per session b0dc400aea99
- 25d ago Changed · +83 lines · +769 tokens per session 6e14eda4ccce
- 2mo ago First seen · 205 lines · 2,944 tokens per session scan A daee6592b1e8
skills AGENTS.md is an instructions file published in the GitHub repository togethercomputer/skills (40 stars, last pushed yesterday), licensed MIT. It adds 3,706 tokens to every session, about $0.0148 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 2026-08-30.
skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skills AGENTS.mdtogethercomputer/skills | Instructions file | 40 | yesterday | MIT | A | 3,706 | Codex, OpenCode |
| 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 | today | 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 |