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/goperigon/perigon-mcp-server/agents-mdgit clone --depth 1 https://github.com/goperigon/perigon-mcp-serverWrote 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/goperigon/perigon-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/goperigon/perigon-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/goperigon/perigon-mcp-server/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 | $0.00442 | $0.00442 |
| Opus 5 | $0.00221 | $0.00221 |
| Sonnet 5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
perigon-mcp-server 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
Agent Guidelines for Perigon MCP Server
Important
DO NOT run the dev server unless explicitly told to DO NOT needlessly build the app for no reason
Build/Test Commands
bun run dev- Start development serverbun run build- Build for productionbun run deploy- Deploy to Cloudflare Workersbun run mcp- Run MCP inspectorbun run gen- Generate Wrangler types- No test framework configured - check with maintainer before adding tests
Code Style
- TypeScript: Strict mode, ES2021 target, avoid
anytypes - React: Functional components with hooks, JSX transform
- Imports: ES modules, prefer named imports, React import required
- Formatting: 2-space indentation, double quotes, camelCase for props/functions
- Components: PascalCase naming, store in
src/components/ - CSS: TailwindCSS with custom tokens (gold, surface, dark themes)
- Error Handling: Use try/catch for async, TypeScript interfaces for validation
Perigon Brand Colors
- Primary:
#227C9D(light),#34B3E2(dark) - Background:
#FBFBF9(light),#1F1F1F(dark) - Text:
#121212(light),#FFFFFF(dark) - Muted:
#44403C(light),#C1C1C1(dark)
Dependencies & Architecture
- Built on Vite + React + TypeScript + TailwindCSS v4
- Cloudflare Workers runtime with Wrangler deployment
- AI SDK (@ai-sdk/react) for chat, MCP SDK for protocol
- No Cursor/Copilot rules configured
Key Patterns
- Use
useChathook from @ai-sdk/react for chat functionality - Custom TailwindCSS design tokens for consistent theming
- Proper TypeScript interfaces for all props and data structures
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 · 40 lines · 442 tokens per session scan A 5e5340e12c92
perigon-mcp-server AGENTS.md is an instructions file published in the GitHub repository goperigon/perigon-mcp-server (6 stars, last pushed 9d ago), licensed Apache-2.0. It adds 442 tokens to every session, about $0.0022 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
worldmonitor AGENTS.md
AGENTS.md instructions for koala73/worldmonitor, covering agents.md, task mode and authority, start here, surface routing and architecture invariants.
ai-research-arm CLAUDE.md
Claude Code instructions for guzus/ai-research-arm, covering claude.md, project overview, core pipeline architecture, key components and scripts (scripts/).
google-news-api AGENTS.md
Instructions for ma2za/google-news-api, covering agent instructions, mandatory context discovery, project, development and releases.
ai-research-arm AGENTS.md
AGENTS.md instructions for guzus/ai-research-arm, covering agents.md and agent-specific notes.
wdoc CLAUDE.md
Claude Code instructions for thiswillbeyourgithub/wdoc, covering claude.md, project overview, commands, install and test.
news-reviewer AGENTS.md
Instructions for mertcanciy/news-reviewer, covering agents.md, news reviewer, input, step 1 — source and step 2 — brief.