agentmods.dev

sdd-steering

A command for creating or updating project memory called steering context. This context records the project's architecture and naming rules, technology stack, and product goals, users, and business background.

In plain words
What is it for?
Use it to create initial steering files, synchronize them after code changes, or review and improve the project's documented structure, technology, and product context.
Why use it?
It gives coding agents a shared reference for how the project is structured and why it exists. It can also detect differences between the documented context and the current codebase.

Command for Claude Code

12 8mo ago A scan 0 tokens original MIT
View the source file nahisaho/CodeGraphMCPServer
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/nahisaho/codegraphmcpserver/sdd-steering
Clone the repo
git clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServer

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,033 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 $0.00000 $0.02033
Opus 5 $0.00000 $0.01017
Sonnet 5 $0.00000 $0.00407
Haiku 4.5 $0.00000 $0.00203

Measured 2d ago against content hash fe7b66004560, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd-steering 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/sdd-steering.md · 357 lines

How it starts

The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD Steering Command

Generate or update project memory (steering context).

Instructions for Claude

You are executing the /sdd-steering command to generate or update the project's steering context.

What is Steering?

Steering provides project memory for all Claude Code skills. It consists of 3 core files that document:

  1. structure.md - Architecture patterns, directory structure, naming conventions
  2. tech.md - Technology stack, frameworks, tools
  3. product.md - Business context, product goals, users

Your Task

Mode Detection: Determine which mode to use:

  1. Bootstrap Mode - No steering files exist

    • Analyze entire codebase
    • Generate initial steering files
    • Create both English (.md) and Japanese (.ja.md) versions

  2. Sync Mode - Steering files exist, codebase has changed

    • Compare current steering with codebase
    • Identify discrepancies
    • Update steering files to match reality
    • Preserve both English and Japanese versions

  3. Review Mode - User wants to review/improve steering

    • Present current steering
    • Suggest improvements
    • Ask user for feedback

Mode 1: Bootstrap (First Time)

Detection

  • steering/ directory doesn't exist OR
  • steering/structure.md, steering/tech.md, steering/product.md don't exist

Steps

  1. Analyze Codebase (use Glob, Grep, Read tools extensively):

    • Directory structure
    • File organization patterns
    • Technology stack (package.json, requirements.txt, go.mod, etc.)
    • Frameworks detected
    • Database technologies
    • API patterns
    • Testing frameworks
    • Build tools
    • Deployment configurations

  2. Infer Product Context:

    • README.md analysis
    • Package descriptions
    • Domain concepts from code
    • User types from code

  3. Generate Steering Files (Bilingual):

    IMPORTANT: Create BOTH English and Japanese versions for each file.

    English version is always the reference/source.

    Create steering/structure.md (English) with:

    • Architecture pattern (monolith, microservices, library-first, etc.)
    • Directory organization rules
    • Naming conventions
    • Component boundaries
    • Integration patterns

Read the full file on GitHub · 357 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 · 357 lines · 0 tokens per session scan A fe7b66004560

Subscribe to this mod's changes

sdd-steering is a command published in the GitHub repository nahisaho/CodeGraphMCPServer (12 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,033 tokens. 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 2026-08-30.

Code reviewMemory and contextPlanning
Related

Other commands, from other repositories

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens

converge

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

github/spec-kit · 35 tokens

implement

Execute the implementation plan by processing and executing all tasks defined in tasks.md.

github/spec-kit · 14 tokens