review-workflow

A required review step for completed software work before it is committed, uploaded, or proposed for merging.

In plain words
What is it for?
It creates a handoff covering the goal, changes, decisions, checks, and limitations; gives the reviewer the code differences and test output; and repeats review after requested revisions.
Why use it?
It adds an independent check for problems after implementation and requires issues to be fixed and rechecked before release steps continue.

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

Made for: Cursor.

Per session 146 This file is loaded in full into every session.
When invoked 146 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 $0.00146 $0.00146
Opus 5 $0.00073 $0.00073
Sonnet 5 $0.00029 $0.00029
Haiku 4.5 $0.00015 $0.00015

Measured 2d ago against content hash 68f6f5d19897, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-workflow 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 2d 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.

.cursor/rules/review-workflow.mdc · 14 lines

What it actually says

Review Workflow Rule

When implementation is complete, run a review loop before commit, push, or PR.

  1. Produce a compact handoff: goal, scope, files changed, key decisions, checks run, known limitations.
  2. Invoke the reviewer sub-agent with fresh context and the shared review contract in prompts/code-review.md.
  3. Provide the reviewer the handoff, git diff --stat, git diff, and any relevant lint/test/build output.
  4. If the reviewer returns Verdict: revise, address the findings, re-run verification, update the handoff, and review again.
  5. Only proceed once the reviewer returns Verdict: accept.
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. 2d ago First seen · 14 lines · 146 tokens per session scan A 68f6f5d19897

Subscribe to this mod's changes

review-workflow is a cursor rule published in the GitHub repository feral-file/ff-cli (5 stars, last pushed 14d ago), licensed MIT. It adds 146 tokens to every session, about $0.0007 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.