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.
git clone --depth 1 https://github.com/sergeionlyart/minius_codex_labnpx agentmods add skills/sergeionlyart/minius_codex_lab/session-memory-handoffWrote 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.
[](https://agentmods.dev/skills/sergeionlyart/minius_codex_lab/session-memory-handoff)<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>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 | $0.00078 | $0.00935 |
| Opus 5 | $0.00039 | $0.00467 |
| Sonnet 5 | $0.00016 | $0.00187 |
| Haiku 4.5 | $0.00008 | $0.00093 |
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.
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
- Из корня прочитай
memory/CURRENT.md,OPEN_QUESTIONS.mdи active matter. - Убедись, что нет незавершенного конфликтующего владельца файлов.
- 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.
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 · 100 lines · 78 tokens per session scan A ca019a331a5b
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.
Other skills, from other repositories
git-ai-search
Search and restore AI conversation context from git history.
github-ops
GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.
mulch-record-from-evidence
Turn the evidence of a finished work session — git commits, changed files, recently-touched seeds issues — into well-formed ml record invocations. Use at session close, when an agent has made changes worth preserving as mulch expertise but hasn't yet recorded them.
release-finalizer
Merges a release PR, associates it with resolved issues, replies to issue reporters, and closes issues. Use after PR review is complete and ready for merge. Closes the release cycle.
release-prep
Orchestrates the full release preparation flow for a plugin — version sync across 7+ files, bilingual release notes creation, and commit message drafting. Use before submitting a PR. Does NOT push or create a PR; that is handled by pr-submitter.
publish-no-version-bump
Commit and push code to GitHub, then publish to OpenWebUI official marketplace without updating version. Use when fixing bugs or optimizing performance that doesn't warrant a version bump.