Borrowing it
Nothing to install: this file belongs to Doris-Labs/sales-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/Doris-Labs/sales-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/Doris-Labs/sales-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/doris-labs/sales-skills/agents-md)<a href="https://agentmods.dev/instructions/doris-labs/sales-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/doris-labs/sales-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/doris-labs/sales-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/doris-labs/sales-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 | $0.00515 | $0.00515 |
| Opus 5.5 | $0.00206 | $0.00206 |
| Sonnet 5.5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
sales-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 2mo 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents guide
This repo is a collection of Claude skills for Account Executives. The skills are designed to work together as an agentic toolkit, and they follow a few shared conventions that make that composition reliable.
sales-context is read first
The sales-context skill holds the foundational facts an AE keeps coming back to:
who the company sells to, the ICP, the sales motion, the stages of the pipeline,
the products, the competitors, and the AE's own deals in flight. Other skills
read this context before doing their own work, so that a discovery, qualification,
or follow-up skill doesn't have to re-establish the basics every time. Treat
sales-context as the shared memory layer the rest of the skills build on. If the
context isn't populated yet, skills should fall back to asking the AE directly.
Skills auto-trigger on their Triggers on: phrases
Every skill declares a description in its frontmatter that ends with a
Triggers on: list of natural-language phrases. Those phrases are how a skill
gets selected automatically: when the AE's request matches one of them, the
corresponding skill activates without anyone naming it explicitly. Write trigger
phrases the way an AE actually talks ("prep me for this call", "is this deal
qualified", "draft a follow-up") so the right skill fires at the right moment.
The three binding tiers degrade gracefully
Each skill can source its data at three levels of integration, and it always degrades gracefully rather than failing:
- Doris (best). The Doris ontology provides the richest, most-connected context — deals, stakeholders, commitments, objections, competitors, meetings, and emails resolved through a single typed layer. This is the recommended path.
- Any other MCP (better). If Doris isn't connected but a CRM, a conversation-intelligence tool, or an email MCP is available, the skill uses that instead. Less complete than Doris, but a real upgrade over manual input.
- Nothing connected (still works). With no integrations at all, the skill asks the AE for the inputs and works from pasted notes, transcripts, and memory. This path is always complete and functional — never a dead end.
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.
- 2mo ago First seen · 43 lines · 515 tokens per session scan A eabe3e28b67b
sales-skills AGENTS.md is an instructions file published in the GitHub repository Doris-Labs/sales-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 515 tokens to every session, about $0.0021 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.
sales-skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sales-skills AGENTS.mdDoris-Labs/sales-skills | Instructions file | 3 | 5mo ago | MIT | A | 515 | 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 |