session-start-current-state

A session-start checklist for checking open pull requests and the current Git repository state before changing code.

In plain words
What is it for?
Use it at the beginning of a coding session to inspect pull requests, branches, recent commits, and uncommitted changes, then show a status summary.
Why use it?
It prevents new work from being started while earlier changes still have failing checks, unresolved reviews, or merge issues.

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/flomenco-inc/flo-plugin/session-start-current-state
Clone the repo
git clone --depth 1 https://github.com/Flomenco-Inc/flo-plugin

Made for: Cursor.

Per session 355 This file is loaded in full into every session.
When invoked 355 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 $0.00355 $0.00355
Opus 5 $0.00178 $0.00178
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00036 $0.00036

Measured yesterday against content hash 46374d507c7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-start-current-state 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/session-start-current-state.mdc · 45 lines

What it actually says

Session Start: Current State Assessment

Before writing any code in a new session, run this checklist. Present the results to the user as a status summary before proceeding.

Step 1 — Open PRs

gh pr list --repo Flomenco-Inc/flo-plugin --state open --author "@me" \
  --json number,title,url,headRefName,reviewDecision \
  --jq '.[] | "\(.number) \(.title) [\(.reviewDecision // "NONE")] \(.url)"'

If any open PRs exist:

  • Failing CI → fix before starting new work.
  • Unresolved review threads → reply and resolve before starting new work.
  • Mergeable → merge now.

Do not start a new task while a previous PR is stalled.

Step 2 — Current branch and git state

git status --short
git branch --show-current
git log --oneline -5

Step 3 — Present the status summary

## Session Status
- Open PRs: <count> (<list with status>)
- Current branch: <branch> (<clean/dirty>)
- Blockers: <none, or list>

Architecture reference

This repo is the @flomenco/claude-plugin-mcp npm package. It connects to the flo API via OAuth. See flo/.cursor/rules/flo-system-architecture.mdc § "Claude plugin bootstrap + package" for how it integrates with the main system.

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 · 45 lines · 355 tokens per session scan A 46374d507c7c

Subscribe to this mod's changes

session-start-current-state is a cursor rule published in the GitHub repository Flomenco-Inc/flo-plugin (0 stars, last pushed 2d ago), licensed MIT. It adds 355 tokens to every session, about $0.0018 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.