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/add-pattern)<a href="https://agentmods.dev/commands/rkaushik29/claude-correct-habits/add-pattern"><img src="https://agentmods.dev/badge/commands/rkaushik29/claude-correct-habits/add-pattern/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.
<a href="https://agentmods.dev/commands/rkaushik29/claude-correct-habits/add-pattern"><img src="https://agentmods.dev/badge/commands/rkaushik29/claude-correct-habits/add-pattern.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00015 | $0.00572 |
| Opus 5 | $0.00008 | $0.00286 |
| Sonnet 5 | $0.00003 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
add-pattern 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 9d 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 - Add Pattern
You are helping the user manually add a coding pattern to the Correct Habits memory.
Process
-
If
$ARGUMENTSis provided, use it as the starting point for the pattern description -
If not, ask the user: "What coding pattern or preference would you like me to remember?"
-
Once you have the description, extract:
- name: A short kebab-case identifier (e.g.,
prefer-const-over-let) - description: Clear, actionable rule
- category: One of: naming, error-handling, architecture, testing, style, imports, other
- bad_example: Code showing what NOT to do (ask if not obvious)
- good_example: Code showing the correct approach (ask if not provided)
- name: A short kebab-case identifier (e.g.,
-
Confirm with the user before saving:
I'll remember this pattern: **[name]**: [description] ❌ Don't: [bad_example] ✓ Do: [good_example] Save this pattern? (yes/no) -
If confirmed, append to
.claude/correct-habits/patterns.json(in the current project directory):
const pattern = {
id: `pat_${Date.now()}_${Math.random().toString(36).slice(2, 8)}`,
name: "[extracted name]",
description: "[extracted description]",
category: "[category]",
bad_example: "[bad example]",
good_example: "[good example]",
confidence: 1.0, // Manual additions are high confidence
reasoning: "Manually added by user",
createdAt: new Date().toISOString(),
hitCount: 0
};
-
Create the directory if it doesn't exist:
mkdir -p .claude/correct-habits -
Read existing file, parse JSON, push new pattern, write back
Example Interaction
User: /add-pattern always use early returns instead of nested if statements
You:
I'll remember this pattern:
**prefer-early-returns**: Use early returns to reduce nesting instead of wrapping code in if statements
❌ Don't:
function process(data) {
if (data) {
if (data.valid) {
// lots of nested code
}
}
}
✓ Do:
function process(data) {
if (!data) return;
if (!data.valid) return;
// flat code
}
Save this pattern? (yes/no)
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.
- 9d ago First seen · 83 lines · 15 tokens per session scan A 2a3229312a11
add-pattern is a command published in the GitHub repository rkaushik29/claude-correct-habits (2 stars, last pushed 7mo ago), licensed MIT. It adds 15 tokens to every session and 572 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.