sync-context

Sync project context to CLAUDE.md by analyzing codebase patterns and conventions.

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/luanmorenommaciel/agentspec/sync-context
Clone the repo
git clone --depth 1 https://github.com/luanmorenommaciel/agentspec

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,782 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 $0.00018 $0.01782
Opus 5 $0.00009 $0.00891
Sonnet 5 $0.00004 $0.00356
Haiku 4.5 $0.00002 $0.00178

Measured yesterday against content hash 7010ff14bd68, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync-context 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/commands/core/sync-context.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync Context Command

Analyzes codebase and intelligently updates CLAUDE.md with current project context.

Usage

/sync-context                    # Full analysis and update
/sync-context --section agents   # Update specific section
/sync-context --dry-run          # Preview changes without saving

What It Does

  1. Analyzes current codebase structure
  2. Extracts patterns, conventions, and architecture
  3. Merges with existing CLAUDE.md content
  4. Preserves manual customizations
  5. Updates sections that need refresh

Analysis Process

Step 1: Scan Codebase Structure

# Discover project structure
Glob("**/*.py")              # Python files
Glob("**/*.ts")              # TypeScript files
Glob("**/package.json")      # Node projects
Glob("**/pyproject.toml")    # Python projects
Glob("**/Dockerfile")        # Container configs
Glob("**/*.tf")              # Terraform

Step 2: Extract Patterns

# Code patterns
Grep("@dataclass")           # Dataclass usage
Grep("class.*Parser")        # Parser patterns
Grep("def test_")            # Test patterns
Grep("async def")            # Async patterns

# Architecture patterns
Grep("from src")             # Import structure
Grep("@router")              # API patterns
Grep("@lambda_handler")      # Lambda patterns

Step 3: Analyze Agents

# List available agents
Glob(".claude/agents/**/*.md")

# Categorize by folder
- workflow/       → SDD pipeline agents (brainstorm, define, design, build, ship, iterate)
- architect/      → System design (schema, pipeline, lakehouse, genai, planner)
- cloud/          → AWS, GCP, CI/CD, deployment agents
- platform/       → Microsoft Fabric specialists
- python/         → Code review, clean, document, prompt engineering
- test/           → Testing, data quality, data contracts
- data-engineering/ → Spark, dbt, Airflow, Lakeflow, streaming, SQL
- dev/            → Codebase explorer, meeting analyst, prompt crafter

Read the full file on GitHub · 348 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 · 348 lines · 18 tokens per session scan A 7010ff14bd68

Subscribe to this mod's changes

sync-context is a command published in the GitHub repository luanmorenommaciel/agentspec (244 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 1,782 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 2026-09-01.