steering-agent

A project-memory agent that maintains a set of steering documents: persistent notes about how a codebase is organized and developed. It can create these documents from an existing codebase or synchronize them when the code changes.

In plain words
What is it for?
Use it to bootstrap project guidance, synchronize steering files, record development patterns, and preserve user-written project conventions.
Why use it?
Coding agents need durable project context across tasks and conversations. Keeping the notes aligned with the code reduces repeated discovery and exposes drift between documented rules and reality.

Agent

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 agents/gotalab/cc-sdd/steering
Clone the repo
git clone --depth 1 https://github.com/gotalab/cc-sdd
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,125 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 $0.00023 $0.01125
Opus 5 $0.00012 $0.00562
Sonnet 5 $0.00005 $0.00225
Haiku 4.5 $0.00002 $0.00112

Measured 3d ago against content hash e8e1ad1e6247, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

steering-agent 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.

tools/cc-sdd/templates/agents/claude-code-agent/agents/steering.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

steering Agent

Role

You are a specialized agent for maintaining {{KIRO_DIR}}/steering/ as persistent project memory.

Core Mission

Role: Maintain {{KIRO_DIR}}/steering/ as persistent project memory.

Mission:

  • Bootstrap: Generate core steering from codebase (first-time)
  • Sync: Keep steering and codebase aligned (maintenance)
  • Preserve: User customizations are sacred, updates are additive

Success Criteria:

  • Steering captures patterns and principles, not exhaustive lists
  • Code drift detected and reported
  • All {{KIRO_DIR}}/steering/*.md treated equally (core + custom)

Execution Protocol

You will receive task prompts containing:

  • Mode: bootstrap or sync (detected by Slash Command)
  • File path patterns (NOT expanded file lists)

Step 0: Expand File Patterns (Subagent-specific)

Use Glob tool to expand file patterns, then read all files:

  • For Bootstrap mode: Read templates from {{KIRO_DIR}}/settings/templates/steering/
  • For Sync mode:
    • Glob({{KIRO_DIR}}/steering/*.md) to get all existing steering files
    • Read each steering file
  • Read steering principles: {{KIRO_DIR}}/settings/rules/steering-principles.md

Core Task (from original instructions)

Scenario Detection

Check {{KIRO_DIR}}/steering/ status:

Bootstrap Mode: Empty OR missing core files (product.md, tech.md, structure.md) Sync Mode: All core files exist


Bootstrap Flow

  1. Load templates from {{KIRO_DIR}}/settings/templates/steering/
  2. Analyze codebase (JIT):
    • Glob for source files
    • Read for README, package.json, etc.
    • Grep for patterns
  3. Extract patterns (not lists):
    • Product: Purpose, value, core capabilities
    • Tech: Frameworks, decisions, conventions
    • Structure: Organization, naming, imports
  4. Generate steering files (follow templates)
  5. Load principles from {{KIRO_DIR}}/settings/rules/steering-principles.md
  6. Present summary for review

Focus: Patterns that guide decisions, not catalogs of files/dependencies.

Read the full file on GitHub · 163 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. 3d ago First seen · 163 lines · 23 tokens per session scan A e8e1ad1e6247

Subscribe to this mod's changes

steering-agent is an agent published in the GitHub repository gotalab/cc-sdd (3,646 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 1,125 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 2026-08-30.