# Correction Intent Tagger

> Detects when a user message corrects a prior one, builds an active state where corrections override originals, and injects only the live instruction set into agent context. Prevents model drift when users change their minds mid-session.

- **Type:** Skill
- **Install:** `agentstack add skill-parad0x-labs-openclaw-skills-correction-intent`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Parad0x-Labs](https://agentstack.voostack.com/s/parad0x-labs)
- **Installs:** 0
- **Category:** [Security](https://agentstack.voostack.com/c/security)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Parad0x-Labs](https://github.com/Parad0x-Labs)
- **Source:** https://github.com/Parad0x-Labs/openclaw-skills/tree/main/plugins/correction-intent

## Install

```sh
agentstack add skill-parad0x-labs-openclaw-skills-correction-intent
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Correction vs Instruction Tagger

Detects when a message corrects a prior one and builds an active state
where corrections override originals.

The problem nobody benchmarks: "use Redis" at msg 20, "actually use
Postgres" at msg 47. Standard compression keeps both. This tagger
supersedes Redis, surfaces only Postgres in activeInstructions.

## Usage

```python
from correction_intent import tag_messages, build_active_state, inject_active_state

tagged = tag_messages(messages)
state = build_active_state(tagged)
system_injection = inject_active_state(state)
# inject into system prompt — agent sees CURRENT STATE, not history
```

## What it detects

- CORRECTION: "actually", "scratch that", "instead", "I meant", implicit topic override
- INSTRUCTION: new directive
- ADDITIVE: "also", "additionally" — extends without overriding
- QUERY: question, not actionable
- ACK: "ok", "got it", "understood"

## Correction chain receipt

```python
from correction_intent import correction_chain_receipt
receipt = correction_chain_receipt(state, session_id)
# receipt["chain_root"] anchors to Solana via receipt_anchor
```

Part of the Parad0x Labs stack: github.com/Parad0x-Labs/openclaw-skills/tree/main/plugins/correction-intent

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Parad0x-Labs](https://github.com/Parad0x-Labs)
- **Source:** [Parad0x-Labs/openclaw-skills](https://github.com/Parad0x-Labs/openclaw-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-parad0x-labs-openclaw-skills-correction-intent
- Seller: https://agentstack.voostack.com/s/parad0x-labs
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.