agentmods.dev

load-rules

A command that loads behavioural rules from RULE.md files into the agent’s working instructions. It checks both the installed plugin location and the repository’s linked rules directory.

In plain words
What is it for?
Use it at the start of work or after context is compacted to load and reapply the project’s behavioural rules.
Why use it?
It prevents the agent from working without required project rules or silently missing rules after the conversation context is shortened.

Command

Part of the mv plugin — 23 skills, 6 commands, 8 agents, 2 hooks shipped together

2 5d ago A scan 22 tokens original Apache-2.0
View the source file infohata/mind-vault
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.

agentmods
npx agentmods add commands/infohata/mind-vault/load-rules
Clone the repo
git clone --depth 1 https://github.com/infohata/mind-vault

Or install mv, the plugin that ships this one along with the rest of its 23 skills, 6 commands, 8 agents, 2 hooks.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 409 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00022 $0.00409
Opus 5 $0.00011 $0.00204
Sonnet 5 $0.00004 $0.00082
Haiku 4.5 $0.00002 $0.00041

Measured 2d ago against content hash c98760ad414e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

load-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 2d 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.

commands/load-rules.md · 44 lines

What it actually says

load-rules

Load the mind-vault behavioural rules into working memory. Works on both distribution channels:

  • Plugin channel — rules ship inside the plugin root. The env var ${CLAUDE_PLUGIN_ROOT} points at the installed/dev plugin root; rules live at ${CLAUDE_PLUGIN_ROOT}/rules/. Rules are NOT auto-loaded on this channel (a plugin has no always-on rules surface), so this command is how they get in.
  • Symlink channel — ~/.claude/rules/ is symlinked to the repo's rules/ and surfaced via ~/.claude/CLAUDE.md. This command reloads them after a context compaction.

Steps to follow:

  1. Resolve the rules directory. In order:

    • If ${CLAUDE_PLUGIN_ROOT} is set and ${CLAUDE_PLUGIN_ROOT}/rules/ exists, use it (plugin channel).
    • Else use the repo-relative rules/ directory (symlink/dev channel).
    • Detect + warn: if neither resolves to a directory containing RULE_*.md, stop and report that no rules were found — name both paths you tried. Do not silently load zero rules.

  2. Glob RULE_*.md in the resolved directory and read the full content of each.

  3. Keep each rule in working memory for this session — its directives apply to every subsequent tool call.

  4. Display a summary of all loaded rules:

    • The resolved rules directory and which channel it implies
    • Each rule name + a brief description
    • Confirm they are active for enforcement

  5. Verify no rules are missing or corrupted.

  6. Provide confirmation that rules have been loaded and are ready for use.

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. 2d ago First seen · 44 lines · 22 tokens per session scan A c98760ad414e

Subscribe to this mod's changes

load-rules is a command published in the GitHub repository infohata/mind-vault (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 22 tokens to every session and 409 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.

Memory and context
Related

Other commands, from other repositories

git

Git operations with intelligent commit messages and workflow optimization.

SuperClaude-Org/SuperClaude_Framework · 11 tokens

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens

converge

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

github/spec-kit · 35 tokens