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/sandraschi/mastodon-mcp/agents-mdgit clone --depth 1 https://github.com/sandraschi/mastodon-mcpWrote 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/sandraschi/mastodon-mcp/agents-md)<a href="https://agentmods.dev/instructions/sandraschi/mastodon-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/mastodon-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.00338 | $0.00338 |
| Opus 5 | $0.00169 | $0.00169 |
| Sonnet 5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
mastodon-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 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.
What it actually says
mastodon-mcp — Agent Guide
Fleet MCP server (Comms / Fediverse). Private until .nopublish lifted.
Overview
FastMCP 3.4+ Mastodon bridge — human-approved outbox for fleet-public-relations-mcp drafts. Ports 10754 / 10755. Pattern sibling of discord-mcp.
Standards
- FastMCP 3.4.4+ portmanteau + skills + prompt + Prefab card
- Dual transport: HTTP
/mcp+ REST; dry-run default - MCPB:
just mcpb-pack· Tauri scaffold:src-tauri/(icons + PyInstaller before native) - No GitHub Actions while private
- Tone: FLEET_PROMOTION.md
Key files
| Path | Role |
|---|---|
src/mastodon_mcp/server.py |
FastAPI + FastMCP |
src/mastodon_mcp/portmanteau.py |
mastodon_social ops |
src/mastodon_mcp/outbox.py |
SQLite outbox |
webapp/ |
Dark UI + Playwright e2e |
INSTALL.md / llms.txt / llms-full.txt |
Install + LLM manifests |
manifest.json / glama.json |
MCPB + discovery metadata |
Quick ref
.\start.ps1
uv run pytest tests/ -q
cd webapp; npm run test:e2e
just mcpb-pack
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 First seen · 36 lines · 338 tokens per session scan A 7ef5ce96df20
mastodon-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/mastodon-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 338 tokens to every session, about $0.0017 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
ActivityPub AGENTS.md
AGENTS.md instructions for TryGhost/ActivityPub, covering activitypub — agent guide, commands, migrations, boundaries — what not to touch and critical gotchas.
bluesky-mcp AGENTS.md
AGENTS.md instructions for sandraschi/bluesky-mcp, covering bluesky-mcp — agent guide, standards, key files and quick ref.
bluesky-mcp CLAUDE.md
Claude Code instructions for sandraschi/bluesky-mcp, covering bluesky-mcp — claude / agent context, do, don't and commands.
bluesky-mcp copilot-instructions.md
Copilot instructions for sandraschi/bluesky-mcp, covering github copilot instructions for bluesky-mcp and session context (bluesky mcp).
contraponto AGENTS.md
AGENTS.md instructions for vepo/contraponto, covering agent instructions (contraponto), agents vs commands, rules — four pillars (always on), file-scoped rules (selected) and project agents.
contraponto CLAUDE.md
Claude Code instructions for vepo/contraponto, covering claude.md, start here, stack, commands and gotchas.