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/amigo-ai/forge-mcp/agents-mdgit clone --depth 1 https://github.com/amigo-ai/forge-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/amigo-ai/forge-mcp/agents-md)<a href="https://agentmods.dev/instructions/amigo-ai/forge-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/amigo-ai/forge-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 | $0.00287 | $0.00287 |
| Opus 5 | $0.00143 | $0.00143 |
| Sonnet 5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
forge-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 4d 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
Forge MCP - Agent Guidelines
This is the MCP server for the Amigo Agent Forge platform. It provides tools for managing AI agents, context graphs, services, and related entities.
OpenAPI Reference
The official API schema is at: https://api.amigo.ai/v1/openapi.json
When adding or modifying entity schemas in src/tools/entity-schemas.ts, always validate field names, types, and required/optional status against the OpenAPI spec. The spec is the source of truth for request payloads.
Architecture
src/tools/entity-schemas.ts— Zod schemas for all entity create/update tool parameterssrc/tools/entity-crud.ts— Tool registration (entity-specific create/update + generic list/get/delete)src/resources/instructions.ts— MCP resource with agent engineering documentationsrc/config/constants.ts— Entity types, API paths, and response key mappingssrc/api/client.ts— HTTP client with retry and pagination
Key Conventions
- Entity-specific tools are named
forge_{entity}_create/forge_{entity}_update - Generic
forge_entity_create/forge_entity_updateremain as fallbacks - Agent updates have special voice_config logic (default applied on initial version only)
- POST to
{id}/creates a new version for agents and context graphs, but updates metadata for other entities
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.
- 4d ago First seen · 25 lines · 287 tokens per session scan A a76e599974b0
forge-mcp AGENTS.md is an instructions file published in the GitHub repository amigo-ai/forge-mcp (0 stars, last pushed 1mo ago), licensed ISC. It adds 287 tokens to every session, about $0.0014 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
openrouter-mcp-multimodal AGENTS.md
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).
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
seekstone CLAUDE.md
Claude Code instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.