agent-readiness

A command that checks how ready a code repository is for development assisted by AI, then offers step-by-step improvements. It organizes guidance across files such as AGENTS.md, README.md, and testing or security documents.

In plain words
What is it for?
Use it to assess or improve repository documentation, add agent instructions, organize project guidelines, and connect those guidelines to tools such as CodeRabbit.
Why use it?
It helps an AI coding agent understand the project’s rules, structure, and working practices instead of relying on incomplete context.

Command 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 commands/xsovad06/sova/agent-readiness
Clone the repo
git clone --depth 1 https://github.com/xsovad06/sova

Made for: Claude Code.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,419 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 $0.00016 $0.01419
Opus 5 $0.00008 $0.00709
Sonnet 5 $0.00003 $0.00284
Haiku 4.5 $0.00002 $0.00142

Measured 2d ago against content hash 672e8477a151, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-readiness 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.

.claude/commands/agent-readiness.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Assess the current repository's readiness for AI-assisted development, then offer to improve it step by step. $ARGUMENTS

Whenever you need to ask the user a question, always use the AskUserQuestion tool -- never ask as plain text.

When a step involves a discussion with the user, tell them they can say "done" or "skip" to move on to the next step.

Step 1. Assess (before)

Present this explanation:

This skill helps you build a layered documentation system for AI-assisted development. Each file has a distinct role:

  • docs/*-guidelines.md -- Detailed, domain-specific playbooks (security, testing, database, etc.) with concrete rules agents follow
  • AGENTS.md -- The onboarding doc for any AI agent: cross-cutting conventions + an index pointing to the guideline files
  • CLAUDE.md -- A thin, Claude Code-specific layer that imports AGENTS.md and adds Claude-only behavior (build commands, etc.)
  • .coderabbit.yaml -- Points CodeRabbit (AI code reviewer) to the guideline files so it enforces your conventions during PR reviews
  • README.md -- The front door: high-level project context for humans and agents alike
  • CONTRIBUTING.md -- Contribution conventions for both humans and agents
  • docs/ARCHITECTURE.md -- Institutional knowledge about the system's design and key architectural decisions

We'll check what's already in place, then walk through each file step by step.

Check every requirement and present results:

# Requirement How to check
1 Domain-specific guideline files (docs/*-guidelines.md) Glob for files -- pass if at least one exists
2 AGENTS.md with AI-specific guidance and docs index Check repo root
3 CLAUDE.md imports AGENTS.md (@AGENTS.md) Check repo root
4 CodeRabbit configured (.coderabbit.yaml) Check for knowledge_base.code_guidelines.filePatterns
5 README.md with foundational context Check repo root
6 CONTRIBUTING.md with contribution conventions Check repo root
7 docs/ARCHITECTURE.md with institutional knowledge Check for file

Read the full file on GitHub · 142 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. 2d ago First seen · 142 lines · 16 tokens per session scan A 672e8477a151

Subscribe to this mod's changes

agent-readiness is a command published in the GitHub repository xsovad06/sova (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,419 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 2026-08-31.