correct

A command that reviews an error notebook containing corrections made during earlier work. It groups active corrections by type and highlights mistakes that keep recurring.

In plain words
What is it for?
Checking writing rules about tone, structure, terminology, and formatting, then reviewing which corrections are most often missed.
Why use it?
It reminds you of known writing problems before you work, so the same errors are less likely to be repeated.

Command

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/helloruru/claude-memory-engine/correct
Clone the repo
git clone --depth 1 https://github.com/HelloRuru/claude-memory-engine
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 224 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 $0.00011 $0.00224
Opus 5 $0.00005 $0.00112
Sonnet 5 $0.00002 $0.00045
Haiku 4.5 $0.00001 $0.00022

Measured 2d ago against content hash 20a463d52539, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

correct 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/correct.md · 22 lines

What it actually says

/correct — Review Error Notebook

Scan your error notebook and remind yourself what you've gotten wrong before.

Steps

  1. Load the error notebook — Read ~/.claude/skills/learned/writing-review-list.md
  2. Filter active items — Skip items marked cleared, only show active ones
  3. Group by category — Group corrections by type (tone, structure, terminology, formatting, etc.)
  4. Summarize — List each active rule with its miss count, most recent example
  5. Flag repeat offenders — Anything missed 3+ times gets highlighted as "needs hard rule"
  6. Report — "N active corrections. Top risks: [list the ones missed most often]."

When to run

  • Runs automatically before each task (you don't need to type anything)
  • Type /correct anytime to manually review — no need to wait for a task or a cycle
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 · 22 lines · 11 tokens per session scan A 20a463d52539

Subscribe to this mod's changes

correct is a command published in the GitHub repository HelloRuru/claude-memory-engine (133 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 224 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 2026-08-30.