agentmods.dev

rules.add

rules.add is a skill for Claude Code from gpsaggese/helpers. It costs 8 tokens per session (401 once invoked), scanned B, original, Apache-2.0.

A workflow for adding a new rule to the project's rule files after choosing the appropriate file and matching its existing structure.

In plain words
What is it for?
Use it to select a target rule file, review its organization, draft the rule, and insert it under the relevant heading.
Why use it?
It prevents new guidance from being placed in the wrong file or written in an inconsistent format.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

not rated 158repo +1 today B scan 8 tokens original Apache-2.0

Good fit Use it to select a target rule file, review its organization, draft the rule, and insert it under the relevant heading.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gpsaggese/helpers/rules.add
View source ↗ gpsaggese/helpers
Install

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.

Any agent
npx skills add gpsaggese/helpers --skill rules.add
Clone the repo
git clone --depth 1 https://github.com/gpsaggese/helpers

Made for: Claude Code.

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 rules.add

README.md
[![agentmods](https://agentmods.dev/badge/skills/gpsaggese/helpers/rules.add/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/rules.add)
Your own site
<a href="https://agentmods.dev/skills/gpsaggese/helpers/rules.add"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/rules.add/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for rules.add

Your own site · 80×15
<a href="https://agentmods.dev/skills/gpsaggese/helpers/rules.add"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/rules.add.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 401 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00008 $0.00401
Opus 5.5 $0.00003 $0.00160
Sonnet 5.5 $0.00002 $0.00080
Haiku 4.5 $0.00001 $0.00040

Measured yesterday against content hash 752dd3fdad55, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

rules.add scanned grade B 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 yesterday.

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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

> ls -1 .claude/skills/*.rules.md
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • rules.add — 89% identical, 37 lines differ
.claude/skills/rules.add/SKILL.md · 47 lines

What it actually says

Goal

  • The user passes:
    • The description of a rule or behavior <CONTENT> to add to a rule file
    • (Optional) The target rule file <TARGET_RULE_FILE>, in the format .claude/skills/*.rules.md

Workflow

Read Skill Rules

  • Read .claude/skills/skill.rules.md for the conventions and rules to write skills

Determine Target Rule File

  • If the user did not specify <TARGET_RULE_FILE>, pick the rule file that fits <CONTENT>
  • The available rules are: 
    > ls -1 .claude/skills/*.rules.md
  • If <CONTENT> fits more than one file equally well, or fits none clearly, do not guess. Ask the user which <TARGET_RULE_FILE> to use, listing the candidate files

Read Target Rule File

  • Read <TARGET_RULE_FILE> to understand its structure and existing rules

Draft the New Rule

  • Draft the rule <CONTENT>, following .claude/skills/markdown.rules.md and .claude/skills/text.rules.md

Add the New Rule

  • Find the proper H1 header related to <CONTENT>
    • See .claude/skills/skill.rules.md ## Keep Rules Organized in the Rule File
  • Add <CONTENT> to <TARGET_RULE_FILE>, following .claude/skills/skill.rules.md
  • Make sure it does not overlap with other rules

Verification

  • <CONTENT> is added under the correct H1 header in <TARGET_RULE_FILE>
  • No existing rule in <TARGET_RULE_FILE> already covers <CONTENT>
  • <TARGET_RULE_FILE> was confirmed with the user, not guessed, if it was ambiguous
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. yesterday First seen · 47 lines · 8 tokens per session scan B 752dd3fdad55

Subscribe to this mod's changes

rules.add is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 8 tokens to every session and 401 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.

Project management
Related

rules.add compared with skills from other repositories

rules.add next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
rules.addgpsaggese/helpersSkill158todayApache-2.0B8Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex