sage-harness-generate

sage-harness-generate is a cursor rule for Cursor from gustavobarbosab/sage. It costs 18 tokens per session (431 once invoked), scanned A, original, MIT.

A SAGE command that examines shared project files and creates a .sage/harness.md file describing the project’s technology, coding conventions, and patterns to avoid. A project harness is a written set of instructions for working consistently in that codebase.

In plain words
What is it for?
Use it to analyze build files, architecture code, UI files, dependency-injection modules, and tests, then generate project guidance with confidence notes and inconsistency warnings.
Why use it?
It records inferred project rules so future coding work can follow the existing structure instead of guessing.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions CLAUDE.md.

Good fit Use it to analyze build files, architecture code, UI files, dependency-injection modules, and tests, then generate project guidance with confidence notes and inconsistency warnings.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/gustavobarbosab/sage/sage-harness-generate
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.

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

Made for: Cursor.

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 sage-harness-generate

README.md
[![agentmods](https://agentmods.dev/badge/rules/gustavobarbosab/sage/sage-harness-generate/github.svg)](https://agentmods.dev/rules/gustavobarbosab/sage/sage-harness-generate)
Your own site
<a href="https://agentmods.dev/rules/gustavobarbosab/sage/sage-harness-generate"><img src="https://agentmods.dev/badge/rules/gustavobarbosab/sage/sage-harness-generate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sage-harness-generate

Your own site · 80×15
<a href="https://agentmods.dev/rules/gustavobarbosab/sage/sage-harness-generate"><img src="https://agentmods.dev/badge/rules/gustavobarbosab/sage/sage-harness-generate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 431 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00018 $0.00431
Opus 5 $0.00009 $0.00216
Sonnet 5 $0.00004 $0.00086
Haiku 4.5 $0.00002 $0.00043

Measured 8d ago against content hash c1b6cfa11209, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sage-harness-generate 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 8d 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/cursor/.cursor/rules/sage-harness-generate.mdc · 66 lines

What it actually says

/sage harness generate

Infers .sage/harness.md by analyzing existing codebase files.

Instructions

Ask the user to share files from their codebase. Suggest the most useful ones:

"Please share some files so I can infer your project conventions. The most useful are:

  • build.gradle.kts / package.json / pyproject.toml (stack and versions)
  • 2–3 ViewModel or state-holding classes (architecture patterns)
  • 2–3 UI files / screens / components (UI conventions)
  • 1–2 DI modules (injection approach)
  • 1–2 test files (test conventions)
  • Any existing .editorconfig, .cursorrules, or CLAUDE.md"

Once files are provided, analyze them and generate .sage/harness.md:

## Project Harness — <inferred project name>

### Stack
- <inferred stack items with versions>

### Conventions
- <naming patterns with examples from the code>
- <architecture rules>

### Avoid
- <patterns NOT found in the code — things deliberately avoided>

Flags to include

Mark inferences with low confidence:

❓ Possibly: <inferred rule> — confirm before adopting

Mark inconsistencies found across files:

⚠️ Inconsistency: <description> — which version is correct?

Rules

  • Only infer what the code actually shows — don't invent conventions
  • The "Avoid" section will be sparse on first generation — that's expected
  • Always flag ❓ and ⚠️ items for the user to resolve before committing

After generation

Tell the user: "Harness drafted at .sage/harness.md. Review every ❓ and ⚠️ item before committing. Run /sage harness review after any major refactor to keep it accurate."

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. 8d ago First seen · 66 lines · 18 tokens per session scan A c1b6cfa11209

Subscribe to this mod's changes

sage-harness-generate is a cursor rule published in the GitHub repository gustavobarbosab/sage (2 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 431 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.