writ-lint-0.8B

writ-lint-0.8B

A fine-tuned Qwen3.5-0.8B model that evaluates the quality of AI agent instructions and generates actionable improvement feedback.

Part of the Tier 2.5 hybrid architecture in enwrit -- the communication layer for AI agents.

How It Works

This model is one half of a hybrid scoring system:

1. LightGBM (bundled in the enwrit CLI) predicts headline + 6 dimension scores (~1ms)
2. writ-lint-0.8B (this model) generates issues (ERROR/WARNING/INFO) and improvement suggestions, using the instruction text and LightGBM-predicted scores as context

The model focuses entirely on generating actionable feedback, not scores. Scores from LightGBM are passed in the prompt so the model can target weak dimensions.

Usage

Via the enwrit CLI (recommended)

pip install enwrit
pip install llama-cpp-python  # CPU inference, ~10s per instruction

writ lint AGENTS.md --deep-local

The model is auto-downloaded to ~/.writ/models/ on first use.

Direct inference with llama-cpp-python

from llama_cpp import Llama
import json

model = Llama(
    model_path="writ-lint-0.8B-Q4_K_M.gguf",
    n_ctx=4096,
    n_gpu_layers=-1,  # GPU acceleration (0 for CPU-only)
    verbose=False,
)

prompt = """<|im_start|>system
You are an expert instruction quality evaluator. Given an instruction and its quality scores, generate specific issues and improvement suggestions.<|im_end|>
<|im_start|>user
## Instruction to evaluate

{instruction_text}

## Quality scores (predicted)

Headline: 52/100
Clarity: 58 | Structure: 65 | Coverage: 42 | Brevity: 71 | Examples: 28 | Verification: 35

Analyze the instruction. Return JSON with "issues" (level + message) and "suggestions".<|im_end|>
<|im_start|>assistant
"""

output = model.create_completion(
    prompt,
    max_tokens=1024,
    temperature=0.3,
    response_format={"type": "json_object"},
)

feedback = json.loads(output["choices"][0]["text"])
print(json.dumps(feedback, indent=2))

Output Format

{
  "issues": [
    {"level": "ERROR", "message": "Missing concrete code examples for error handling patterns."},
    {"level": "WARNING", "message": "Verification steps are subjective rather than binary."},
    {"level": "INFO", "message": "Consider adding a 'Rules' section for behavioral constraints."}
  ],
  "suggestions": [
    "Add a 'Code Examples' section with 'Good vs Bad' patterns for the most critical rules.",
    "Replace subjective verification with specific CLI commands (e.g., `pytest`, `ruff check`).",
    "Include numeric thresholds for measurable constraints (e.g., 'max 100 lines per function')."
  ]
}

Training Details

Evaluation

Compared against retrieval-based approaches (v1/v2/v3) on a held-out validation set:

Key strengths:

• 100% JSON parse success (via constrained decoding)
• Generates novel, context-specific feedback (not limited to seen examples)
• Weak-dimension targeting: 0.47 (issues correlate with low-scoring dimensions)
• Low domain mismatch: 0.014 (doesn't give coding feedback to non-coding instructions)

Scoring Dimensions

The 6 quality dimensions (scored by LightGBM, targeted by this model):

Files

• writ-lint-0.8B-Q4_K_M.gguf -- Quantized model for inference (504 MB)

Links

• enwrit CLI -- Open-source CLI tool
• enwrit.com -- Platform with Hub, AI scoring, and more
• PyPI -- pip install enwrit

License

MIT