spec-driven

A rule for using a specification-first development process on substantial FF1-CLI changes. The process writes down the intended behavior before tests and implementation begin.

In plain words
What is it for?
Use it for large features, major workflow changes, broad refactors, and architectural work. It requires reviewing project documentation, creating tasks, adding or updating tests, implementing the change, and verifying it.
Why use it?
It reduces the chance of starting large changes without understanding the existing code, constraints, required behavior, or how the result will be checked.

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/feral-file/ff-cli/spec-driven
Clone the repo
git clone --depth 1 https://github.com/feral-file/ff-cli

Made for: Cursor.

Per session 254 This file is loaded in full into every session.
When invoked 254 The same file — it is already loaded in full.
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 $0.00254 $0.00254
Opus 5 $0.00127 $0.00127
Sonnet 5 $0.00051 $0.00051
Haiku 4.5 $0.00025 $0.00025

Measured yesterday against content hash 10d2a55b53a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-driven 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.

.cursor/rules/spec-driven.mdc · 28 lines

What it actually says

Spec-Driven Development Rule

Apply this rule for large features, major flow changes, broad refactors, and architectural work.

Required planning workflow

  1. Read docs/PROJECT_SPEC.md.
  2. Read the relevant docs and source files for the area being changed.
  3. Summarize the current behavior, constraints, and invariants.
  4. Write or update a short spec or design note in the handoff if no formal spec exists.
  5. Break the work into concrete tasks.
  6. Identify expected behaviors and how they will be verified.
  7. Add or update tests before implementation where behavior changes.
  8. Then implement and verify.

Canonical sequence: spec -> design -> tasks -> tests -> implementation -> verification

Enforcement

  • Do not start large changes without first summarizing the current state.
  • If docs and implementation conflict, use the implemented behavior as the current-state baseline and note the mismatch.
  • Do not invent new permanent architecture or API policies; those sections are reserved as TBD by repo owner.
  • If a design choice or constraint is important enough to shape future amendments, preserve it in code comments near the affected logic.
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 · 28 lines · 254 tokens per session scan A 10d2a55b53a4

Subscribe to this mod's changes

spec-driven is a cursor rule published in the GitHub repository feral-file/ff-cli (5 stars, last pushed 14d ago), licensed MIT. It adds 254 tokens to every session, about $0.0013 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.