What is pn-session-handoff?

A session handoff guide that records completed work, unfinished tasks, important context, and questions for whoever continues later.

Use it to create a handoff document after long tasks, multi-topic work, loops, or when another person must resume the project.

It prevents the next developer or agent from repeating discovery or missing unresolved work when a session ends.

pn-session-handoff — Skill for Cursor by perniemann

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.

Any agent

npx skills add perniemann/pnCore --skill pn-session-handoff

Clone the repo

git clone --depth 1 https://github.com/perniemann/pnCore

Made for: Cursor.

Or install pn-core, the plugin that ships this one along with the rest of its 133 skills, 19 commands, 9 agents, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/perniemann/pncore/pn-session-handoff/github.svg)](https://agentmods.dev/skills/perniemann/pncore/pn-session-handoff)

Your own site

<a href="https://agentmods.dev/skills/perniemann/pncore/pn-session-handoff"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-session-handoff/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/perniemann/pncore/pn-session-handoff"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-session-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 797 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.00797
Opus 5	$0.00030	$0.00398
Sonnet 5	$0.00012	$0.00159
Haiku 4.5	$0.00006	$0.00080

Measured 6d ago against content hash 5289364c69ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pn-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 6d 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.

packages/pn-core-mcp/content/skills/learning/pn-session-handoff/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session handoff

When used as a standalone skill, begin every response with [pn-skill] 🔺

When to use

Before ending a long or multi-topic session.
When switching tasks and another session (or colleague) must resume cold.
After /loop or build work where .pncore/handoff.md should capture loop STATE pointers.
Not for blameless mistake taxonomy — use pn-session-retro (/pn-retro) instead.

Mission

Produce a handoff document the next session can read without re-discovery, then ask the two reflection questions so blind spots surface before close. Do not auto-edit skills or rules; recommend follow-ups in prose.

Output path

Default: .pncore/handoff.md (project root .pncore/, not repo-root-only ignore — same tree as workflow state).

If the user names a path, use it. Offer to commit when the team shares handoffs.

Two reflection questions

Ask the user (or answer yourself from transcript evidence) after drafting the handoff:

Coverage gap: What are the most important things I should have asked you but didn't?
Blind spot: What did we assume wrong, skip verifying, or leave dangling that could bite the next session?

Keep answers specific — reference files, commands, or STATE paths, not vague summaries.

Handoff document template

# Handoff — <topic slug> (<YYYY-MM-DD>)

## Status
<one paragraph: shipped, in flight, broken>

## Shipped
- <item> — <one sentence>

## In flight
- <item> — where it stopped

## Broken state — fix before continuing
- <dangling ref or half-done wiring> — how to fix

## Decisions
- <decision> — <reason>

## Deferred
- <item> — resurface trigger

## Open questions
- …

## Loop STATE pointers
- `.pncore/loops/<id>/STATE.md` — <one line each, or "none">

## Resume here
<concrete first action: file, command, or question>

Workflow

Inventory — Scan recent tool calls, modified files, open todos, failing commands, active loops under .pncore/loops/.
Dangling check — Any imports, routes, or docs pointing at unfinished work? List under Broken state.
Write handoff — Fill template; quote Resume here and Broken state back to the user.
Two questions — Present coverage gap and blind spot; incorporate user answers into Open questions if new.
Offer next steps — Optional pn-continual-learning if a durable preference emerged; optional /pn-retro if the session felt off.

Read the full file on GitHub · 89 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.

6d ago First seen · 89 lines · 59 tokens per session scan A 5289364c69ca

Subscribe to this mod's changes

pn-session-handoff is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 797 once invoked, about $0.0003 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 2026-09-03.

LLM Planning Productivity TypeScript agents cursor mcp plugin

codex-docs-drift-scout

Install the AutoHub docs-drift Codex automation from signed AutoVault skill resources and audit its render fidelity with autovault doctor.

autoworks-ai/autovault · 36 tokens

typescript

TypeScript coding conventions, best practices, and patterns for writing clean, maintainable code.

genkit-ai/genkit · 20 tokens

output-meta-project-context

Comprehensive guide to Output.ai Framework for building durable, LLM-powered workflows orchestrated by Temporal. Covers project structure, workflow patterns, steps, LLM integration, HTTP clients, CLI commands, and the full inventory of available agents and skills.

growthxai/output · 54 tokens

pn-session-handoff