sage-code

A command rule that generates code from a specification file and a behavior file. It first checks that all unresolved questions in the behavior file have been answered.

In plain words
What is it for?
Use it after requirements are documented to produce code and tests for the specified scenarios. It also applies the project's stated technology, naming, architecture, acceptance criteria, and restrictions.
Why use it?
It prevents code from being generated while important requirements are still undecided. This helps keep the implementation aligned with the agreed behavior and project conventions.

Cursor rule for Cursor

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

Made for: Cursor.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 407 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 $0.00013 $0.00407
Opus 5 $0.00006 $0.00204
Sonnet 5 $0.00003 $0.00081
Haiku 4.5 $0.00001 $0.00041

Measured yesterday against content hash aae3d1437213, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sage-code 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 yesterday.

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-code.mdc · 67 lines

What it actually says

/sage code

Generates production-ready code from spec.md + behavior.md.

Gate check (REQUIRED before generating)

Read behavior.md and check for unresolved open questions (- [ ] items).

If any - [ ] items remain:

⚠️ Cannot generate code — open questions remain in behavior.md:
   • <question 1>
   • <question 2>

Mark each question resolved with [x] in behavior.md, then run /sage code again.

Stop. Do not generate any code.

Only proceed when all open questions are marked [x] or removed.


Instructions

Read:

  • Harness (.sage/harness.md, CLAUDE.md, .cursorrules, or project knowledge)
  • spec.md
  • behavior.md (all resolved scenarios)

Generate production-ready code that:

  1. Follows harness conventions EXACTLY — stack, naming patterns, architecture, restrictions
  2. Implements every acceptance criterion from spec.md
  3. Satisfies every scenario in behavior.md with corresponding test code
  4. Includes previews/examples where the harness requires them
  5. Respects every "Do NOT" item from spec.md

Output format

Return files in this format — each file preceded by its path:

// FILE: <relative/path/to/File.kt>
<file content>

// FILE: <relative/path/to/FileTest.kt>
<file content>

Do not include explanations between files unless asked. Do not deviate from the harness architecture.


After generation

Tell the user: "Code generated. Review it against the acceptance criteria in spec.md — point by point, not by gut feel. Use /sage update <feedback> for any changes needed. When it's ready, run /sage pr and /sage doc to export."

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. yesterday First seen · 67 lines · 13 tokens per session scan A aae3d1437213

Subscribe to this mod's changes

sage-code is a cursor rule published in the GitHub repository gustavobarbosab/sage (2 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 407 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.