harness-init

harness-init is a command for Claude Code from gustavobarbosab/sage. It costs 0 tokens per session (526 once invoked), scanned A, original, MIT.

An interactive setup command that creates a .sage/harness.md file describing a project's technical conventions and constraints.

In plain words
What is it for?
It helps configure project guidance by asking the developer a series of questions and saving the answers for future work.
Why use it?
It gives a coding agent explicit information about the project's language, framework, architecture, state handling, navigation, testing, naming rules, and things to avoid.

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/gustavobarbosab/sage/harness-init
Clone the repo
git clone --depth 1 https://github.com/gustavobarbosab/sage

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 harness-init

README.md
[![agentmods](https://agentmods.dev/badge/commands/gustavobarbosab/sage/harness-init.svg)](https://agentmods.dev/commands/gustavobarbosab/sage/harness-init)
Your own site
<a href="https://agentmods.dev/commands/gustavobarbosab/sage/harness-init"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/harness-init.svg" alt="Measured on agentmods" height="20"></a>
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 526 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 $0.00526
Opus 5 $0.00000 $0.00263
Sonnet 5 $0.00000 $0.00105
Haiku 4.5 $0.00000 $0.00053

Measured 4d ago against content hash c7b566c2ad83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness-init 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 4d 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.

skill/claude-code/.claude/commands/sage/harness-init.md · 55 lines

What it actually says

/sage harness init

Creates .sage/harness.md via an interactive wizard.

Instructions

Ask the user the following questions one at a time. Wait for each answer before asking the next.

  1. "What's your primary language and version? (e.g. Kotlin 2.0, TypeScript 5.4)"
  2. "What UI framework or runtime are you using? (e.g. Jetpack Compose BOM 2024.06, React 18, none)"
  3. "How do you handle dependency injection? (e.g. Hilt, Inversify, manual, none)"
  4. "What architecture pattern do you follow? (e.g. MVI, MVVM, Clean Architecture)"
  5. "How do you manage state? (e.g. StateFlow, Redux, Zustand, signals)"
  6. "How does navigation work? (e.g. lambda callbacks, NavController, React Router)"
  7. "What's your async/concurrency approach? (e.g. Kotlin Coroutines + Flow, async/await)"
  8. "What test framework do you use? (e.g. JUnit5 + MockK + Turbine, Jest + RTL)"
  9. "What naming conventions do you follow for key files? (e.g. ViewModels, Screens, Tests)"
  10. "What should I avoid? (e.g. LiveData, XML views, Material2, hardcoded strings)"
  11. "Anything else I should always know about this project?"

After collecting all answers, generate .sage/harness.md:

## Project Harness — <project name>

### Stack
- <bullet list of stack items>

### Conventions
- <naming patterns>
- <architecture rules>
- <required practices>

### Avoid
- <anti-patterns>
- <deprecated APIs>
- <things explicitly out of scope>

Rules

  • Every rule must be checkable in code review — no vague guidance
  • The "Avoid" section is often more valuable than "Conventions"
  • Start lean — the harness can always be extended later
  • Save to .sage/harness.md at the project root

After generation

Tell the user: "Harness saved to .sage/harness.md. Commit it to version control so your whole team shares the same conventions. Run /sage harness review periodically to catch drift. Now run /sage spec <feature description> to start your first feature."

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. 4d ago First seen · 55 lines · 0 tokens per session scan A c7b566c2ad83

Subscribe to this mod's changes

harness-init is a command published in the GitHub repository gustavobarbosab/sage (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 526 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 2026-08-31.