# Learn

> Record router misclassifications to ~/.claude/imlazy/heuristics.log so the router adapts over time. Invoked by workflow skills on auto-escalation or on user feedback

- **Type:** Skill
- **Install:** `agentstack add skill-hnikoloski-imlazy-imlazy-learn`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [hnikoloski](https://agentstack.voostack.com/s/hnikoloski)
- **Installs:** 0
- **Category:** [Productivity](https://agentstack.voostack.com/c/productivity)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [hnikoloski](https://github.com/hnikoloski)
- **Source:** https://github.com/hnikoloski/imlazy/tree/main/skills/imlazy-learn
- **Website:** https://hnikoloski.github.io/imlazy/

## Install

```sh
agentstack add skill-hnikoloski-imlazy-imlazy-learn
```

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

## About

# learn

## When to invoke

1. **Auto-escalation fired:** the router classified Quick, work started, verification failed, escalated to Standard. Log it.
2. **User feedback:** user signals classification was wrong ("this didn't need all that ceremony" or "this was bigger than you thought"). Log it.

## What to write

Append one line to `~/.claude/imlazy/heuristics.log` (create the directory if needed):

```
\t\t\t
```

Example:
```
2026-05-15T14:32:00Z	quick	standard	add a /health endpoint
```

## Implementation

```bash
mkdir -p ~/.claude/imlazy
printf '%s\t%s\t%s\t%.50s\n' \
  "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
  "$PREDICTED_TIER" \
  "$ACTUAL_TIER" \
  "$TASK_SUMMARY" \
  >> ~/.claude/imlazy/heuristics.log
```

## How the router uses it

`lazy-router` reads the last 20 lines of this file on every classification. Recent (≤30 days) misclassification patterns shift borderline classifications toward the tier that turned out correct in similar past cases.

## What NOT to log

- Successful classifications — signal-to-noise only (log misclassifications only).
- Task content beyond 50 chars — truncation limits accidental leakage of sensitive task descriptions.

## Source & license

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

- **Author:** [hnikoloski](https://github.com/hnikoloski)
- **Source:** [hnikoloski/imlazy](https://github.com/hnikoloski/imlazy)
- **License:** MIT
- **Homepage:** https://hnikoloski.github.io/imlazy/

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-hnikoloski-imlazy-imlazy-learn
- Seller: https://agentstack.voostack.com/s/hnikoloski
- 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%.