Borrowing it
Nothing to install: this file belongs to noblepayne/mcp-injector. 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/noblepayne/mcp-injector/main/AGENTS.mdgit clone --depth 1 https://github.com/noblepayne/mcp-injectorWrote 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/noblepayne/mcp-injector/agents-md)<a href="https://agentmods.dev/instructions/noblepayne/mcp-injector/agents-md"><img src="https://agentmods.dev/badge/instructions/noblepayne/mcp-injector/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 | $0.07776 | $0.07776 |
| Opus 5 | $0.03888 | $0.03888 |
| Sonnet 5 | $0.01555 | $0.01555 |
| Haiku 4.5 | $0.00778 | $0.00778 |
Grade A, and why
mcp-injector AGENTS.md scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
[babashka.curl :as curl] How it starts
The opening of the file, as written. The whole thing — 1,039 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - mcp-injector
"Simple is the opposite of complex. Easy is the opposite of hard." — Rich Hickey
Philosophy: Grumpy Pragmatism
We write situated programs that are reliable, robust, and data-driven. We reject OOP nonsense in favor of simple, composable systems. This codebase follows the philosophy of grumpy senior developers who've been burned by complexity:
Research-First Workflow (Shotgun Pattern)
"AI coding tools make you fast at building. They don't make you fast at knowing what to build."
Before implementing major features, ALWAYS follow this workflow:
1. Ask: "Does this already exist?"
- Don't assume you need to build from scratch
- Search for existing solutions (libraries, proxies, frameworks)
- The answer is often "yes, it's called X"
2. Research Phase
Before writing ANY code for a new feature:
- Read the existing codebase to understand current patterns
- Search for existing solutions in the ecosystem
- Check if similar functionality exists elsewhere
- Ask clarifying questions if requirements are unclear
3. Specify Phase
Write a spec before coding that includes:
- What already exists in the codebase
- What needs to be built
- Acceptance criteria
- Edge cases to handle
4. Break Big Changes into Staged PRs
- Don't ship monster PRs
- Break features into reviewable chunks
- Each stage should be independently testable
Example Research Workflow
User: We need usage tracking for LLM calls
Agent (should ask first):
- Does this already exist? Let me search...
- Found: LiteLLM Proxy has built-in usage tracking
- Alternative: Build custom (3-4 weeks) vs integrate LiteLLM (5 days)
- Recommendation: Use LiteLLM
Peer Review Process
We value external review from senior colleagues. Before merging significant changes, we prepare a comprehensive review bundle to get a "stern but fair" stamp of approval.
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.
- 7d ago First seen · 1,039 lines · 7,776 tokens per session scan A decd2218ae0f
mcp-injector AGENTS.md is an instructions file published in the GitHub repository noblepayne/mcp-injector (5 stars, last pushed 4d ago), licensed MIT. It adds 7,776 tokens to every session, about $0.0389 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.