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 agentmods add instructions/rendobar/mcp/agents-mdgit clone --depth 1 https://github.com/rendobar/mcpWhat 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 | $0.00940 | $0.00940 |
| Opus 5 | $0.00470 | $0.00470 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
mcp 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 yesterday.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — @rendobar/mcp
Guide for agents and humans working on the Rendobar MCP server. Companion to the monorepo guide at rendobar/rendobar. Dev rules, build/test commands, and the MCP-specific hard bans live in CLAUDE.md — read it before changing code.
TL;DR
- What this is: the local stdio Model Context Protocol server for Rendobar. Single ESM bundle, ~6 tools, public, MIT.
- SDK source: lives in the rendobar/rendobar monorepo under
packages/sdk/. Consumed here as@rendobar/sdkfrom npm. - Release: conventional commits → release-please → npm publish with provenance +
.mcpbGitHub Release asset + official MCP registry. - No manual tags, no manual version bumps. release-please owns them.
The rules that bite (full detail in CLAUDE.md)
- Never write to stdout. It is reserved for JSON-RPC framing; one stray byte kills the connection. Logs go to stderr.
- Recoverable tool failures return
{ isError: true }, not throws. Throw only for programmer bugs. - Cold-start budget < 2 s, bundle < 100 KB. CI asserts both. No network calls at module load.
- One Zod version. The SDK uses
zod/v4; two copies breakregisterTool. Fix the dep tree, neveras any.
Cross-repo brand consistency
This repo is part of the broader Rendobar platform. The canonical reference for brand strings, URLs, and metadata across every rendobar repo is the apex monorepo's .claude/rules/brand-consistency.md:
https://github.com/rendobar/rendobar/blob/main/.claude/rules/brand-consistency.md
Canonical brand strings (must match apex)
| Field | Value |
|---|---|
| Display name | Rendobar |
| Slogan | Media processing API for developers and agents |
| Apex URL | https://rendobar.com |
| Apex page URLs | https://rendobar.com/<path>/ (always trailing slash) |
| API URL | https://api.rendobar.com |
| Dashboard URL | https://app.rendobar.com |
| CDN URL | https://cdn.rendobar.com |
| Twitter handle | @rendobar |
| Discord | https://discord.gg/kAGqjBzx8N |
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.
- yesterday First seen · 61 lines · 940 tokens per session scan A 8297c353955b
mcp AGENTS.md is an instructions file published in the GitHub repository rendobar/mcp (1 stars, last pushed yesterday), licensed MIT. It adds 940 tokens to every session, about $0.0047 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
video-agent-runtime AGENTS.md
AGENTS.md instructions for YansIlinta/video-agent-runtime, covering repository rules for coding agents, start with the narrowest relevant context, authoritative architecture, llm and edit-state rules and provider rules.
ffmpeg-mcp-lite CLAUDE.md
Instructions for kevinwatt/ffmpeg-mcp-lite, covering claude.md, project overview, technology stack, development commands and install dependencies.
palmier-pro-windows AGENTS.md
AGENTS.md instructions for MadeNavaneeth/palmier-pro-windows, covering palmier pro windows agent guide, mandatory upstream check, upstream dispositions, translation rules and required finish checks.
broll CLAUDE.md
Instructions for luke-fairbanks/broll, covering broll — architecture rules, non-negotiables, layout, conventions and known sharp edges.
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).