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.
git clone --depth 1 https://github.com/rkaushik29/claude-correct-habitsWrote 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/commands/rkaushik29/claude-correct-habits/patterns)<a href="https://agentmods.dev/commands/rkaushik29/claude-correct-habits/patterns"><img src="https://agentmods.dev/badge/commands/rkaushik29/claude-correct-habits/patterns.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 | $0.00012 | $0.00378 |
| Opus 5 | $0.00006 | $0.00189 |
| Sonnet 5 | $0.00002 | $0.00076 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
patterns 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 8d 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.
What it actually says
Correct Habits - Pattern Management
You are helping the user manage their learned coding patterns stored by the Correct Habits plugin.
Available Actions
Based on $ARGUMENTS:
list (default)
Read the patterns file at .claude/correct-habits/patterns.json (in the current project directory) and display all patterns in a readable format:
- Group by category
- Show name, description, and examples
- Include hit count and when it was learned
search <query>
Search patterns by name, description, or category. Show matching results.
remove <pattern-name-or-id>
Remove a pattern by its name or ID. Confirm with the user before deleting.
export
Export all patterns as a markdown file that could be added to CLAUDE.md
Instructions
- Read the patterns file:
.claude/correct-habits/patterns.json - Parse the JSON and perform the requested action
- Format output clearly for the user
- If the file doesn't exist, inform the user no patterns have been learned yet
File Format Reference
{
"patterns": [
{
"id": "pat_xxx",
"name": "pattern-name",
"description": "What the pattern enforces",
"category": "naming|error-handling|architecture|testing|style|imports|other",
"bad_example": "code to avoid",
"good_example": "preferred code",
"confidence": 0.85,
"hitCount": 5,
"createdAt": "ISO date"
}
]
}
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.
- 8d ago First seen · 54 lines · 12 tokens per session scan A 0de2c561618f
patterns is a command published in the GitHub repository rkaushik29/claude-correct-habits (2 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 378 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.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.