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/f0rty-tw0/agentic-mcp/agents-mdgit clone --depth 1 https://github.com/F0rty-Tw0/agentic-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/f0rty-tw0/agentic-mcp/agents-md)<a href="https://agentmods.dev/instructions/f0rty-tw0/agentic-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/f0rty-tw0/agentic-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 | $0.02231 | $0.02231 |
| Opus 5 | $0.01115 | $0.01115 |
| Sonnet 5 | $0.00446 | $0.00446 |
| Haiku 4.5 | $0.00223 | $0.00223 |
Grade A, and why
agentic-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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Coding Conventions
Things You Will Get Wrong
- No enums, no namespaces —
erasableSyntaxOnlyis on. You will try to write enums. Don't. - No classes — use functions and plain objects. The only exception is
Errorsubclasses (they needinstanceofand stack traces). - No default exports — all exports are named, inline on the declaration.
- No extensions on relative imports — use
'./foo', never'./foo.ts'or'./foo.js'. Package imports keep their original extension. node:prefix mandatory — alwaysimport from 'node:fs/promises', never bare'fs/promises'.import typefor type-only imports — enforced byverbatimModuleSyntax. You will forget this.- No
import type * asnamespace imports — import the specific types directly. If a type is reused across files in one top-level module, move it into that module'scommon/folder and import it from there. Do not reach fortypeof import('./foo')or module-wide type namespaces when a direct type import would tell the truth. catch (error: unknown)— neverany, never bareError.toStrictEqualovertoEqual— always. UsetoBefor primitives.- No
eslint-disablecomments — fix the code instead. Refactor to reduce complexity, extract helpers, restructure loops. - No JSDoc, no block comments (
/* */), no commented-out code. - camelCase for local variables — never
snake_case. Map to snake_case keys only at the object-literal boundary:{ working_directory: workingDirectory }.
File & Naming
- Files:
kebab-case.tswith role suffix:.const.ts,.type.ts,.schema.ts,.handler.ts,.builder.ts,.util.ts. - Constants:
SCREAMING_SNAKE_CASE. Types:PascalCase. Functions:camelCase. - Barrel
index.tsat four levels:- Module root (
ask/index.ts): wildcard re-exports from subdirs (export * from './common'). domain-logic/: named re-exports only — this is the module's public API surface for executable behavior. Export functions/constants only; reusable types belong incommon/.common/,utils/,stubs/: named re-exports, no wildcards.utils/index.tsexports functions only; never re-export types there.
- Module root (
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 · 87 lines · 2,231 tokens per session scan A c528c8c7d1a5
agentic-mcp AGENTS.md is an instructions file published in the GitHub repository F0rty-Tw0/agentic-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 2,231 tokens to every session, about $0.0112 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
agentic-playwright enums.instructions.md
Instructions for idavidov13/agentic-playwright, covering enums, critical, file locations, instructions and phase 1: decide if the value belongs in an enum.
agentic-playwright refactor-values.instructions.md
Instructions for idavidov13/agentic-playwright, covering refactoring enum values and static test data, critical, instructions, phase 1: find all consumers before touching anything and find all usages of the enum key.
zod-skill AGENTS.md
Instructions for anivar/zod-skill, covering zod v4 — complete guide, abstract, 1. parsing & type safety, rule: use safeparse() for user input and rule: use parseasync for async refinements.
Zod Schema Conventions
Use when editing or creating Zod schemas, adding tool argument validation, modifying enum normalization, or deriving MCP inputSchema in this repository.
Kokoro-Engine CLAUDE.md
Claude Code instructions for chyinan/Kokoro-Engine, covering claude.md, git 规范, 项目概述, 常用命令 and 安装依赖.
retry-axios GEMINI.md
Gemini CLI instructions for JustinBeckwith/retry-axios, covering project: retry-axios, project overview, building and running, dependencies and commands.