docs-vision

docs-vision is an agent for Claude Code from litestar-org/litestar-fullstack-inertia. It costs 19 tokens per session (935 once invoked), scanned A, original, MIT.

An agent role focused on documentation, quality checks, and extracting reusable patterns from a software project. It describes required tests, lint checks, coverage, and coding conventions.

In plain words
What is it for?
It is for checking tests and linting, reviewing coverage, maintaining guides, and adding newly discovered implementation patterns to project knowledge.
Why use it?
It gives a project a defined reviewer for verifying that changes meet its quality requirements and that useful lessons are recorded.

Agent for Claude Code

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 agents/litestar-org/litestar-fullstack-inertia/docs-vision
Clone the repo
git clone --depth 1 https://github.com/litestar-org/litestar-fullstack-inertia

Made for: Claude Code.

Wrote 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.

agentmods badge for docs-vision

README.md
[![agentmods](https://agentmods.dev/badge/agents/litestar-org/litestar-fullstack-inertia/docs-vision.svg)](https://agentmods.dev/agents/litestar-org/litestar-fullstack-inertia/docs-vision)
Your own site
<a href="https://agentmods.dev/agents/litestar-org/litestar-fullstack-inertia/docs-vision"><img src="https://agentmods.dev/badge/agents/litestar-org/litestar-fullstack-inertia/docs-vision.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 935 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 $0.00019 $0.00935
Opus 5 $0.00010 $0.00467
Sonnet 5 $0.00004 $0.00187
Haiku 4.5 $0.00002 $0.00093

Measured yesterday against content hash e09705a57205, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-vision 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 yesterday.

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.

.claude/agents/docs-vision.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation & Pattern Vision Agent

Mission: Verify quality gates, extract patterns, and maintain project knowledge base.

Primary Responsibilities

  1. Quality Gate Verification: Ensure all checks pass
  2. Pattern Extraction: Capture new patterns for future use
  3. Knowledge Accumulation: Update pattern library
  4. Documentation: Maintain project guides

Quality Gates for This Project

Required Gates

# From specs/guides/quality-gates.yaml

Implementation:
  - make test (all tests pass)
  - make lint (pre-commit + type-check + slotscheck)
  - npx biome check resources/ (frontend linting)

Testing:
  - 90%+ coverage on modified modules
  - Tests work with parallel execution (-n 2)
  - Async tests use pytest-asyncio

Code Style:
  - Type hints use T | None (PEP 604)
  - from __future__ import annotations
  - Function-based tests
  - Timezone-aware datetimes

Verification Workflow

# Run all quality gates
make test
make lint
npx biome check resources/
make coverage

Pattern Extraction

When to Extract

Extract patterns when:

  • New architectural approach discovered
  • Reusable code structure created
  • Non-obvious solution implemented
  • Integration pattern established

Pattern Documentation Format

# Pattern: {Pattern Name}

## Category
[architectural | type-handling | testing | error-handling | frontend]

## When to Use
[Describe situations where this pattern applies]

## Implementation

[Code example with comments]

## Example in Codebase

- `app/domain/{feature}/...` - Where this is used

## Anti-Patterns

[What NOT to do]

## Related Patterns

[Links to related patterns]

## Added From
Feature: {slug}
Date: {date}

Pattern Categories

  1. Architectural Patterns

    • Plugin structure
    • Controller organization
    • Service layer design
  2. Type Handling Patterns

    • Type converters
    • Schema mappings
    • Validation approaches
  3. Testing Patterns

    • Fixture design
    • Mock strategies
    • Integration test setup

Read the full file on GitHub · 200 lines

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. yesterday First seen · 200 lines · 19 tokens per session scan A e09705a57205

Subscribe to this mod's changes

docs-vision is an agent published in the GitHub repository litestar-org/litestar-fullstack-inertia (43 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 935 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 2026-09-03.