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 rules/gustavobarbosab/sage/sage-specgit clone --depth 1 https://github.com/gustavobarbosab/sageWrote 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/rules/gustavobarbosab/sage/sage-spec)<a href="https://agentmods.dev/rules/gustavobarbosab/sage/sage-spec"><img src="https://agentmods.dev/badge/rules/gustavobarbosab/sage/sage-spec.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 | $0.00013 | $0.00930 |
| Opus 5 | $0.00006 | $0.00465 |
| Sonnet 5 | $0.00003 | $0.00186 |
| Haiku 4.5 | $0.00001 | $0.00093 |
Grade A, and why
sage-spec 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sage spec
Generates spec.md + behavior.md through a structured interview — all questions shown upfront, files generated together after answers are collected.
Inline argument
The user may provide an initial description inline:
/sage spec "Login screen with email and password"
/sage spec [paste of Jira ticket content]
If no argument is provided, ask: "What feature do you want to specify?"
Step 1 — Analyze and prepare questions
Read the harness from .sage/harness.md (or CLAUDE.md, .cursorrules, or project knowledge).
Analyze the description and identify everything you need to know to write a complete, unambiguous spec. Do NOT generate the spec yet.
Prepare questions across these categories:
- Purpose & scope — what the feature does and what it explicitly doesn't do
- Inputs & outputs — parameters, types, callbacks, events
- Acceptance criteria — testable conditions for each behavior
- Restrictions — forbidden patterns, anti-patterns, out-of-scope items
- Edge cases — boundary conditions, error states, concurrent actions
Step 2 — Present all questions at once
Show all questions in a single message. Format:
I have X questions before writing your spec and behavior files.
Answer them all and I'll generate both at once.
─────────────────────────────────────────
Question 1 of X
─────────────────────────────────────────
[Category: Purpose & scope]
<Question text>
─────────────────────────────────────────
Question 2 of X
─────────────────────────────────────────
[Category: Inputs & outputs]
<Question text>
... (all questions)
─────────────────────────────────────────
Reply with your answers (numbered or in order) and I'll generate
spec.md and behavior.md together.
─────────────────────────────────────────
Rules for questions:
- Only ask what you genuinely can't infer from the description and harness
- Skip questions whose answers are obvious from context
- Minimum 3, maximum 10 questions — be thorough but not exhausting
- Each question must be specific and answerable in 1-2 sentences
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.
- 4d ago First seen · 158 lines · 13 tokens per session scan A 49f22823c61b
sage-spec 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 930 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.