rules

rules is a skill for Claude Code from Marcel-Bich/marcel-bich-claude-marketplace. It costs 179 tokens per session (1,506 once invoked), scanned A, original, MIT.

A set of project-specific rules stored in a repository's .credo/RULES.md file. The rules can grant the coding agent extra permission for that project.

In plain words
What is it for?
Use it to define and load local operating rules, such as when the agent may restart development services without asking.
Why use it?
It lets a repository carry its own instructions and avoids applying rules from the wrong working directory.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the credo plugin — 26 skills, 15 commands, 6 hooks shipped together

Good fit Use it to define and load local operating rules, such as when the agent may restart development services without asking.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Marcel-Bich/marcel-bich-claude-marketplace
Claude Code
/plugin install credo

Made for: Claude Code.

Or install credo, the plugin that ships this one along with the rest of its 26 skills, 15 commands, 6 hooks.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/rules/github.svg)](https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/rules)
Your own site
<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/rules"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/rules/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

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/rules"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 179 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,506 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 $0.00179 $0.01506
Opus 5 $0.00089 $0.00753
Sonnet 5 $0.00036 $0.00301
Haiku 4.5 $0.00018 $0.00151

Measured 11d ago against content hash 5a7311065345, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

rules 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 11d 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.

plugins/credo/skills/rules/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rules - per-repo credo special rules

A project can carry its own credo special rules in <target>/.credo/RULES.md: a free-form Markdown file of project-local grants that widen credo's autonomy for that one repo. Example: a debug-only repo declaring that restarting local services is always fine without asking. These rules are credo-native and independent of dogma; they travel with the repo (the file is versioned by default).

Resolve the file via the project layer (never cwd)

RULES.md lives in the RESOLVED target .credo/, not necessarily the cwd. Resolve it with the shared project-layer resolver so it also works when you start from a launch hub:

"${CLAUDE_PLUGIN_ROOT}/scripts/credo-config.sh" rules
  • Prints <target>/.credo/RULES.md plus (present) / (missing).
  • Exit 4 = no target resolved (cwd is a hub or has no credo project). Then the rules cannot be located here - the user pins the target with /credo:project <path> (or sets CREDO_DIR), and you retry. Do NOT fall back to reading a cwd-relative file.

When it prints a (present) path, Read that file. Resolution precedence is the same as for config and items: CREDO_DIR env > session pin (/credo:project) > repo-root .credo/.

Config values live in the cascade, not the repo folder

All config and personal values (ntfy topic/server, sleep, identities, viewports) live in the credo config cascade (builtin < global < profile < project). Resolve them ONLY via credo-config.sh get <dotted.key> - never grep the plugin/repo folder, the template holds empty placeholders. To send an ntfy push, use the helper ${CLAUDE_PLUGIN_ROOT}/scripts/credo-ntfy-send.sh "message" (it resolves the topic/server through the cascade and is a silent no-op when ntfy is not configured).

Load and honor at session start

At the start of a session, resolve and (if present) Read .credo/RULES.md, then honor its grants for the whole session. A grant relaxes what you would otherwise ask about or avoid - apply it as if the user had stated it directly, because they did (in that repo). If the file is missing, there simply are no special rules; carry on with credo defaults.

Read the full file on GitHub · 122 lines

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. 11d ago First seen · 122 lines · 179 tokens per session scan A 5a7311065345

Subscribe to this mod's changes

rules is a skill published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed yesterday), licensed MIT. It adds 179 tokens to every session and 1,506 once invoked, about $0.0009 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 2026-08-30.