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.
npx agentmods add commands/spideynolove/claude-dotfiles/steeringgit clone --depth 1 https://github.com/spideynolove/claude-dotfilesWrote 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.
[](https://agentmods.dev/commands/spideynolove/claude-dotfiles/steering)<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>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.
| Model | Per session | Once 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 |
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.
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 (
--syncor files exist): Update to match current code state
Bootstrap Flow
-
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/nullRead: README, package.json/pyproject.toml/go.mod, 2-3 source files for conventions
-
Generate 3 files from templates in
32-cc-sdd-patterns/steering-templates/:product.md— purpose, core value, user types, non-goalstech.md— stack table, architectural decisions, coding conventionsstructure.md— directory pattern, naming, imports
-
Golden rule: Document patterns, not catalogs.
- ❌ "List every file in src/"
- ✅ "Feature-first layout: each feature owns its components, hooks, and tests"
-
Present summary for user review.
Sync Flow
- Read all existing
.claude/steering/*.md - Detect drift:
- New framework/library added → update
tech.md - New directory pattern → update
structure.md - Scope changed → update
product.md
- New framework/library added → update
- Update additively — add sections, never replace user content
- 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.
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.
- 5d ago First seen · 79 lines · 14 tokens per session scan A f579f90a0011
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.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.