steering

steering is a command for Claude Code from spideynolove/claude-dotfiles. It costs 14 tokens per session (585 once invoked), scanned A, original, MIT.

A command for creating or updating persistent project notes in .claude/steering/, covering the product, technology choices, and code structure.

In plain words
What is it for?
Use it to bootstrap project documentation from an existing codebase or sync the notes with current code and architecture.
Why use it?
It keeps important project decisions and conventions available across planning sessions, reducing repeated explanations and inconsistent implementation.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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/spideynolove/claude-dotfiles/steering
Clone the repo
git clone --depth 1 https://github.com/spideynolove/claude-dotfiles

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 steering

README.md
[![agentmods](https://agentmods.dev/badge/commands/spideynolove/claude-dotfiles/steering.svg)](https://agentmods.dev/commands/spideynolove/claude-dotfiles/steering)
Your own site
<a href="https://agentmods.dev/commands/spideynolove/claude-dotfiles/steering"><img src="https://agentmods.dev/badge/commands/spideynolove/claude-dotfiles/steering.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 585 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 $0.00014 $0.00585
Opus 5 $0.00007 $0.00293
Sonnet 5 $0.00003 $0.00117
Haiku 4.5 $0.00001 $0.00059

Measured 5d ago against content hash f579f90a0011, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 5d 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-global-backup/commands/steering.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/steering — Project Memory Management

Maintain .claude/steering/ as persistent project knowledge loaded by every planning command.

Three files: product.md (purpose/value/non-goals) · tech.md (stack/decisions/conventions) · structure.md (layout/naming/imports)

Scenario Detection

Check .claude/steering/ status:

  • Bootstrap: Empty or missing core files → generate from codebase
  • Sync (--sync or files exist): Update to match current code state

Bootstrap Flow

  1. Analyze codebase to extract patterns:

    # Understand structure
    find . -maxdepth 3 -type f -name "*.json" | grep -E "package|pyproject|go.mod" | head -5
    ls src/ 2>/dev/null || ls app/ 2>/dev/null || ls lib/ 2>/dev/null
    

    Read: README, package.json/pyproject.toml/go.mod, 2-3 source files for conventions

  2. Generate 3 files from templates in 32-cc-sdd-patterns/steering-templates/:

    • product.md — purpose, core value, user types, non-goals
    • tech.md — stack table, architectural decisions, coding conventions
    • structure.md — directory pattern, naming, imports
  3. Golden rule: Document patterns, not catalogs.

    • ❌ "List every file in src/"
    • ✅ "Feature-first layout: each feature owns its components, hooks, and tests"
  4. Present summary for user review.


Sync Flow

  1. Read all existing .claude/steering/*.md
  2. Detect drift:
    • New framework/library added → update tech.md
    • New directory pattern → update structure.md
    • Scope changed → update product.md
  3. Update additively — add sections, never replace user content
  4. Report: what changed, what drifted, what to consider

Usage in Planning

Every planning command (create_plan, implement_plan, etc.) should read steering first:

Read .claude/steering/product.md, tech.md, structure.md before planning.

This gives consistent project memory across sessions without loading the full codebase each time.


Output Format

✅ Steering [Created/Updated]

Generated:
- product.md: [1-line summary]
- tech.md: [key stack]
- structure.md: [organization pattern]

Review and treat as source of truth for planning sessions.

Read the full file on GitHub · 79 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. 5d ago First seen · 79 lines · 14 tokens per session scan A f579f90a0011

Subscribe to this mod's changes

steering is a command published in the GitHub repository spideynolove/claude-dotfiles (2 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 585 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.