session-memory-handoff

session-memory-handoff is a skill for Claude Code, Codex from sergeionlyart/minius_codex_lab. It costs 78 tokens per session (935 once invoked), scanned A, original, Apache-2.0.

A way to preserve the important state of a coding session across branches, worktrees, and handoffs. A handoff is a short note that tells the next person what changed, what was checked, what remains, and what could block the work.

In plain words
What is it for?
Use it to start and close research or development sessions, create session notes and meaningful Git commits, update current-work records, and prepare a concise handoff.
Why use it?
It prevents long-running or parallel work from depending on chat history or undocumented decisions. It gives another reviewer enough information to continue safely without exposing secrets or raw logs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/start_session.py --slug <short-slug> --matter <matter-id> --create-branch.

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/sergeionlyart/minius_codex_lab
agentmods
npx agentmods add skills/sergeionlyart/minius_codex_lab/session-memory-handoff

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 session-memory-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/sergeionlyart/minius_codex_lab/session-memory-handoff.svg)](https://agentmods.dev/skills/sergeionlyart/minius_codex_lab/session-memory-handoff)
Your own site
<a href="https://agentmods.dev/skills/sergeionlyart/minius_codex_lab/session-memory-handoff"><img src="https://agentmods.dev/badge/skills/sergeionlyart/minius_codex_lab/session-memory-handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 935 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 5.1 $0.00078 $0.00935
Opus 5 $0.00039 $0.00467
Sonnet 5 $0.00016 $0.00187
Haiku 4.5 $0.00008 $0.00093

Measured 6d ago against content hash ca019a331a5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

session-memory-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.

.agents/skills/session-memory-handoff/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Межсессионная память и handoff

Contract

  • Job-to-be-done: сохранить минимальное устойчивое состояние и передать работу без сырых логов и скрытых решений.
  • Inputs: session objective, branch/worktree, выполненные изменения, tests, риски и next action.
  • Outputs: session log, обновленный CURRENT/index при необходимости и короткий handoff.
  • Evidence and safety: не записывай секреты, raw prompts/tool logs и лишние персональные данные; сверяй memory с Git.
  • Stop conditions: остановись, если session ID/path неоднозначен, есть конфликт владельцев или handoff раскроет restricted data.
  • Acceptance test: новый reviewer вручную восстанавливает branch, scope, проверки, blockers и следующий шаг только из handoff.

Принцип

Git хранит воспроизводимое состояние, memory/ — краткую смысловую карту. Chat transcript не является источником истины.

Начало сессии

  1. Из корня прочитай memory/CURRENT.md, OPEN_QUESTIONS.md и active matter.
  2. Убедись, что нет незавершенного конфликтующего владельца файлов.
  3. Создай session note и ветку:
python3 scripts/start_session.py --slug <short-slug> --matter <matter-id> --create-branch

Для параллельной работы предпочтительно:

git worktree add ../<project>-wt-<slug> -b session/YYYYMMDD-<slug> main

Не включай confidential facts в slug/path. 4. В session note зафиксируй objective, inputs, files owned, planned skills/roles и evidence gate.

Во время работы

Коммить завершенные смысловые этапы:

  • matter: scope/plan;
  • source: source register/import/version;
  • research: analysis/corpus/data code;
  • evidence: claim-evidence mapping;
  • draft: coherent draft milestone;
  • review: audit findings/fixes;
  • decision: durable accepted decision;
  • memory: session/CURRENT handoff;
  • artifact: reproducible generated output;
  • ops: configuration/tooling.

Commit message должен отвечать «какой устойчивый результат появился». Не смешивай unrelated changes. Не коммить пустой checkpoint ради ритуала.

Read the full file on GitHub · 100 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. 6d ago First seen · 100 lines · 78 tokens per session scan A ca019a331a5b

Subscribe to this mod's changes

session-memory-handoff is a skill published in the GitHub repository sergeionlyart/minius_codex_lab (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 78 tokens to every session and 935 once invoked, about $0.0004 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.