Custom-MCPs: Skill for Claude Code

.agents/skills/new-agent-rule/SKILL.md

new-agent-rule is a skill for Claude Code, Codex from Edison-Watch/Custom-MCPs. It costs 28 tokens per session (412 once invoked), scanned A, original, MIT.

A guide for creating path-scoped rules for Claude Code. These rules apply only when the agent works on files matching specified patterns, such as an API or test directory.

In plain words
What is it for?
Use it to create, name, format, and synchronize rules stored in .claude/rules/ and .agents/rules/.
Why use it?
It keeps general project instructions shorter and prevents unrelated guidance from being loaded for every task.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents).

This is Edison-Watch/Custom-MCPs's own configuration. It tells Claude Code and Codex how to work on Custom-MCPs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Custom-MCPs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Edison-Watch/Custom-MCPs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Edison-Watch/Custom-MCPs/main/.agents/skills/new-agent-rule/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Edison-Watch/Custom-MCPs

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for new-agent-rule

README.md
[![agentmods](https://agentmods.dev/badge/skills/edison-watch/custom-mcps/new-agent-rule.svg)](https://agentmods.dev/skills/edison-watch/custom-mcps/new-agent-rule)
Your own site
<a href="https://agentmods.dev/skills/edison-watch/custom-mcps/new-agent-rule"><img src="https://agentmods.dev/badge/skills/edison-watch/custom-mcps/new-agent-rule.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 412 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.00412
Opus 5 $0.00014 $0.00206
Sonnet 5 $0.00006 $0.00082
Haiku 4.5 $0.00003 $0.00041

Measured 7d ago against content hash 0be3c6a092c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

new-agent-rule 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 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.

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.

.agents/skills/new-agent-rule/SKILL.md · 48 lines

What it actually says

Creating a new path-scoped rule

Rules keep CLAUDE.md lean by scoping guidance to specific file paths. A rule applies when the agent touches files matching its globs: pattern.

When to create a rule

  • Guidance applies to a specific directory or file pattern, not the whole repo
  • The guidance is long enough that embedding it in CLAUDE.md would bloat the file
  • Multiple agents (or future tools) should pick up the same guidance automatically

Naming and location

  • Source of truth: .claude/rules/<name>.md
  • Name: snake_case.md describing the area (e.g., api_routes.md, test_conventions.md)
  • Mirror: .agents/rules/<name>.md (symlink, created by make sync-agent-config)

Frontmatter format

Use globs: (NOT paths: -- it has known silent-failure bugs):

---
description: One-line summary of what this rule covers
globs:
  - "src/api/**"
  - "tests/api/**"
---

Pick the narrowest set of globs that covers the area. Overly broad globs waste context on unrelated tasks.

Workflow

  1. Check if CLAUDE.md already covers this guidance (if so, migrate it to a rule)
  2. Write .claude/rules/<name>.md with globs: frontmatter
  3. Run make sync-agent-config then make ci

Anti-patterns

  • Forgetting globs: frontmatter (rule loads on every task, defeating the purpose)
  • Restating what CLAUDE.md already says (keep rules additive, not duplicative)
  • Using paths: instead of globs: (known silent-failure bugs in Claude)
Changes

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.

  1. 7d ago First seen · 48 lines · 28 tokens per session scan A 0be3c6a092c6

Subscribe to this mod's changes

new-agent-rule is a skill published in the GitHub repository Edison-Watch/Custom-MCPs (0 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 412 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens