session-handoff

A rule for preparing a handoff document when a long coding session or major program phase is ending.

In plain words
What is it for?
It is for documenting work before context runs low, after many tool calls, or when a major change has been pushed to version control.
Why use it?
It preserves the mission, architecture, APIs, and current state so the next session does not need to rediscover the project.

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/alphabitcore/nexus-gateway/session-handoff
Clone the repo
git clone --depth 1 https://github.com/AlphaBitCore/nexus-gateway

Made for: Cursor.

Per session 775 This file is loaded in full into every session.
When invoked 775 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 $0.00775 $0.00775
Opus 5 $0.00387 $0.00387
Sonnet 5 $0.00155 $0.00155
Haiku 4.5 $0.00077 $0.00077

Measured 2d ago against content hash 963b7b40be90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-handoff 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/session-handoff.mdc · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session handoff at context-full

Canonical text lives in CLAUDE.md under Mandatory rules. This rule is the IDE-side surfacing; when this file disagrees with CLAUDE.md, CLAUDE.md wins.

When to trigger

Proactively offer the handoff workflow when any of these apply:

  • The conversation is approaching the auto-compact threshold (the assistant senses long context, ~150k+ tokens, or the IDE / harness signals "context full").
  • A multi-phase program is closing out (e.g., the OSS-readiness review's Phase 4 capstone).
  • Tool-call turn count is high (>~50 turns of accumulated state).
  • A major git push just landed work the next session needs to build on.

What the handoff document contains

Typical location: docs/handoffs/program-name.md for repo-tracked plans, or <program-area>/HANDOFF.md for area-local plans, or /tmp/<program>-handoff.md for local-only (less reliable).

Required sections (mirror the canonical example):

  1. Mission — program goal + current phase.
  2. Architecture model — load-bearing facts the next session needs to design / debug against without re-reading the whole codebase. Keep dense (tables ok).
  3. API / surface inventory — what the program operates on.
  4. Work units catalog — concrete units the next session executes (scenarios, modules, tasks).
  5. Existing infrastructure — what to build on, what to avoid rewriting.
  6. Binding rules — pointers into CLAUDE.md + memory anchors the next session must load.
  7. Recent changes affecting the work — renames, deletions, contract changes since the program plan was first drafted.
  8. Suggested program structure — phases + first concrete steps.
  9. Repo state snapshot — branch / tip commit / known dirty WIP from parallel sessions.

Why on-disk, not just memory

  • Maintainer-local memory persists across sessions but is one-line indexed; can't carry a 300-line architecture map.
  • Auto-compact summarizes the conversation but loses fidelity on specifics (file paths, struct fields, contract details).
  • An on-disk handoff document is the single source of truth the next session reads. Memory anchor + on-disk plan together = full handoff.

Read the full file on GitHub · 57 lines

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 · 57 lines · 775 tokens per session scan A 963b7b40be90

Subscribe to this mod's changes

session-handoff is a cursor rule published in the GitHub repository AlphaBitCore/nexus-gateway (22 stars, last pushed 7d ago), licensed Apache-2.0. It adds 775 tokens to every session, about $0.0039 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 2026-08-30.