Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add dribbaengineering/dribba --skill markdown-negotiationgit clone --depth 1 https://github.com/dribbaengineering/dribbaWrote 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/skills/dribbaengineering/dribba/markdown-negotiation)<a href="https://agentmods.dev/skills/dribbaengineering/dribba/markdown-negotiation"><img src="https://agentmods.dev/badge/skills/dribbaengineering/dribba/markdown-negotiation/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/skills/dribbaengineering/dribba/markdown-negotiation"><img src="https://agentmods.dev/badge/skills/dribbaengineering/dribba/markdown-negotiation.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 | $0.00033 | $0.00431 |
| Opus 5.5 | $0.00013 | $0.00172 |
| Sonnet 5.5 | $0.00007 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
markdown-negotiation 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 1mo 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.
What it actually says
Markdown for Agents — Dribba
Any public page on https://dribba.com supports HTTP content negotiation
between HTML and Markdown.
When to use this skill
Use it when you want the prose of a specific page without HTML: send
Accept: text/markdown to any page URL, or append .md (/servicios.md).
Do not use it for structured records — services, case studies, jobs as typed
JSON — that is the rest-api skill. Do not use it to ingest the whole site in
one pass either; walk the okf bundle instead.
How to request markdown
Send an HTTP GET request with an Accept: text/markdown header (or with
markdown weighted equal to or higher than text/html):
GET / HTTP/1.1
Host: dribba.com
Accept: text/markdown
Response
HTTP/1.1 200 OK
Content-Type: text/markdown; charset=utf-8
x-markdown-tokens: <integer — rough token estimate>
Vary: Accept
The response body is a markdown rendering of the page's main content. Script, style, SVG, navigation, footer, and iframe elements are stripped before conversion.
Notes
- Every localized URL is supported (
/,/ca/...,/en/...). - Redirects (301/302/307/308) are forwarded.
- The estimate in
x-markdown-tokensassumes ~4 characters per token and is intended as a hint, not a billing measurement.
Reference
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.
- 1mo ago First seen · 57 lines · 33 tokens per session scan A bf03758b1622
markdown-negotiation is a skill published in the GitHub repository dribbaengineering/dribba (0 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 431 once invoked, about $0.0001 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.
Other skills, from other repositories
voiden
Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.
api-interface-design
Use when designing public APIs, module boundaries, provider adapters, tool schemas, or data contracts.
aiox-architect
Architect (Aria). Use for system architecture (fullstack, backend, frontend, infrastructure), technology stack selection (technical evaluation), API design (REST/GraphQL/tRPC/We...
aiox-data-engineer
Database Architect & Operations Engineer (Dara). Use for database design, schema architecture, Supabase configuration, RLS policies, migrations, query optimization, data modelin...
mcp-bash
Build, debug and package MCP servers written in Bash with the mcp-bash framework (mcp-bash-framework). Use whenever the user wants to create an MCP server from shell scripts or CLIs, add or fix tools, resources, prompts or completions in an mcp-bash project, wire one into Claude Desktop, Cursor or another client…
hatch3r-api-spec
Generates and validates OpenAPI specifications from codebase. Covers endpoint design, schema validation, and documentation generation.