codebase-sync

codebase-sync is a skill for Claude Code from a5c-ai/babysitter. It costs 32 tokens per session (531 once invoked), scanned A, original, MIT.

A codebase analysis workflow that discovers project structure, coding patterns, and development rules, then turns them into enforceable checks.

In plain words
What is it for?
Use it to inspect languages, frameworks, tools, tests, APIs, architecture, and style rules in a codebase.
Why use it?
It reduces the risk of new code conflicting with the project's existing conventions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

About the project

Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.

a5c-ai/babysitter · 1,772 stars · on GitHub · a5c.ai

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 skills/a5c-ai/babysitter/codebase-sync
Any agent
npx skills add a5c-ai/babysitter --skill codebase-sync
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

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 codebase-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/a5c-ai/babysitter/codebase-sync.svg)](https://agentmods.dev/skills/a5c-ai/babysitter/codebase-sync)
Your own site
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/codebase-sync"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/codebase-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 531 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 5.1 $0.00032 $0.00531
Opus 5 $0.00016 $0.00266
Sonnet 5 $0.00006 $0.00106
Haiku 4.5 $0.00003 $0.00053

Measured 3d ago against content hash ebd1b7cfdb89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

codebase-sync 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 3d 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.

library/methodologies/pilot-shell/skills/codebase-sync/SKILL.md · 65 lines

What it actually says

  • Scan directory structure for project type identification
  • Detect language, framework, package manager
  • Identify build tools, CI/CD config, test framework
  • Map high-level architecture (monorepo, microservices, etc.)

2. Semantic Index Building

Four parallel index domains:

  • Code Index: Source files with exports, purposes, dependencies
  • Test Index: Test files with cases, fixtures, patterns
  • Config Index: Configuration files with parsed rules
  • API Index: Public interfaces, types, data models

3. Convention Discovery

  • Code style patterns (naming, structure, organization)
  • Error handling conventions
  • Testing conventions (naming, structure, assertions)
  • Git commit message conventions
  • Documentation standards
  • Language-conditional standards

4. Rule Generation

Convert conventions into enforceable rules:

{
  "id": "ts-no-any",
  "category": "coding-standards",
  "description": "Avoid 'any' type; use 'unknown' and narrow",
  "severity": "error",
  "autoFixable": false,
  "language": "typescript"
}

Rule Categories

Category Examples
core task-and-workflow, testing, verification
dev-practices development-practices, context-management
tools research-tools, cli-tools
coding-standards Language-specific rules (conditional)

Output Artifacts

  • artifacts/CONVENTIONS.md -- Discovered conventions
  • artifacts/SEARCH-INDEX.json -- Semantic search index
  • artifacts/RULES.md -- Generated project rules
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 65 lines · 32 tokens per session scan A ebd1b7cfdb89

Subscribe to this mod's changes

codebase-sync is a skill published in the GitHub repository a5c-ai/babysitter (1,772 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 531 once invoked, about $0.0002 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.