openplan-handoff

openplan-handoff is a skill for Claude Code, Codex from BANANASJIM/openplan-skill. It costs 91 tokens per session (476 once invoked), scanned A, original, MIT.

A compact handoff document for passing unfinished work between coding agents, sessions, or reviewers. It records the goal, decisions, files, evidence, blockers, and next safe action.

In plain words
What is it for?
It helps resume work after a session ends, delegate a task, switch agents, or preserve which files and sources are authoritative.
Why use it?
It prevents the next person or agent from having to reconstruct context from a long conversation or from making guesses about the current state.

Skill for Claude CodeCodex

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 skills/bananasjim/openplan-skill/openplan-handoff
Any agent
npx skills add BANANASJIM/openplan-skill --skill openplan-handoff
Clone the repo
git clone --depth 1 https://github.com/BANANASJIM/openplan-skill

Made for: Claude Code, Codex.

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.

agentmods badge for openplan-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/bananasjim/openplan-skill/openplan-handoff.svg)](https://agentmods.dev/skills/bananasjim/openplan-skill/openplan-handoff)
Your own site
<a href="https://agentmods.dev/skills/bananasjim/openplan-skill/openplan-handoff"><img src="https://agentmods.dev/badge/skills/bananasjim/openplan-skill/openplan-handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 476 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00091 $0.00476
Opus 5 $0.00046 $0.00238
Sonnet 5 $0.00018 $0.00095
Haiku 4.5 $0.00009 $0.00048

Measured 5d ago against content hash 4762aefc9ead, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openplan-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 5d 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.

skills/openplan-handoff/SKILL.md · 59 lines

What it actually says

OpenPlan Handoff

Use this after $openplan-core and $openplan-operate when another agent or future session needs to resume without inheriting a long conversation.

Snapshot Rule

A handoff snapshot is not a memory bank and not a full transcript. It is the smallest durable artifact that lets the next agent decide what to read and what not to assume.

When To Create

  • Before ending a long session.
  • Before delegating to a subagent with non-trivial context.
  • After an auto/YOLO review run.
  • Before context compaction.
  • When switching between Codex and Claude Code.
  • When dual-surface state matters and the next agent must know which surface is authoritative.

Snapshot Contents

Use references/snapshot-template.md unless the user gives a project-native template.

Required sections:

  • Objective
  • Current mode
  • Authority surfaces
  • Human decisions
  • Non-decisions
  • Artifacts touched or reviewed
  • Evidence
  • Open questions and blockers
  • Next safe action
  • Residual risk

Rules

  • Prefer path references over pasted content.
  • Mark stale or unverified facts explicitly.
  • Do not include secrets, credentials, or private tokens.
  • Do not record guesses as decisions.
  • Do not say approved; say reviewed scope and result.
  • If dual repo or dual surface exists, record both surfaces separately.
  • If no write occurred, say so.

Claude Code

Use assets/claude-code-command.md as a slash command or prompt seed.

Use $openplan-html-brief when the same snapshot needs a human-friendly visual frontend.

Use $openplan-record when a handoff lesson should be promoted into durable memory or documentation.

Use $openplan-garden when a handoff or document needs a semantic quality check before another agent relies on it.

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 59 lines · 91 tokens per session scan A 4762aefc9ead

Subscribe to this mod's changes

openplan-handoff is a skill published in the GitHub repository BANANASJIM/openplan-skill (4 stars, last pushed 3mo ago), licensed MIT. It adds 91 tokens to every session and 476 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens