A session-resume skill that restores work from a HANDOFF file, task packet, and recent journal entries after a chat ends or is cleared.

Resuming a previous project task, reopening a closed handoff, and continuing work in a new chat.

It avoids losing the essential state of an ongoing task between chats. If the saved information is missing, too old, or contradictory, it reports that instead of guessing.

pf-resume — Skill for Claude Code and Codex by turvodnik

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 turvodnik/pf-handoff --skill pf-resume

Clone the repo

git clone --depth 1 https://github.com/turvodnik/pf-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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/turvodnik/pf-handoff/pf-resume/github.svg)](https://agentmods.dev/skills/turvodnik/pf-handoff/pf-resume)

Your own site

<a href="https://agentmods.dev/skills/turvodnik/pf-handoff/pf-resume"><img src="https://agentmods.dev/badge/skills/turvodnik/pf-handoff/pf-resume/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/turvodnik/pf-handoff/pf-resume"><img src="https://agentmods.dev/badge/skills/turvodnik/pf-handoff/pf-resume.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 542 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	$0.00092	$0.00542
Opus 5	$0.00046	$0.00271
Sonnet 5	$0.00018	$0.00108
Haiku 4.5	$0.00009	$0.00054

Measured 11d ago against content hash b1a0f1b638cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pf-resume 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 11d 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/pf-resume/SKILL.md · 23 lines

What it actually says

pf-resume — continue as if the chat never ended

Always communicate with the user in the user's language (Russian in the origin system). HANDOFF and status formats stay as specified.

Restores working state from the HANDOFF file (§13). The context is minimal by design: HANDOFF + task packet + 3 days of journal. The old chat's tail is not needed — the HANDOFF must contain everything essential; anything missing is a blocker, not a license to guess. Full context-budget rules (window thresholds, HANDOFF format, subagent swarms) — ../pf-handoff/references/context-rules.md next to this skill; read it when working with swarms or planning large chunks.

Steps

Find the HANDOFF: by the slug argument (if it is closed — reopen it by returning status: active: coming back to a former task is legitimate), otherwise the freshest status: active in the project's .agents/runtime/handoff/. None active — say so and offer the §8 start (journal + packets); that is not an error.
Read the HANDOFF in full; if task: is filled — read the task packet; 3 days of journal — by headers, details as needed.
HANDOFF older than 7 days, or contradicting packet statuses/journal — do not continue silently: list the discrepancies to the human in one message and wait. Its task already done/cancelled — close the file yourself (status: closed) and say so in one line: no litter in the session.
Tell the human two lines: «Продолжаю: <цель>. Следующий шаг: <из HANDOFF>» — and work. Obey the «Не делать» section strictly: those are cancelled directions, do not re-propose them.
At the first milestone or §13 threshold rewrite the HANDOFF via pf-handoff — it is live again.

Forbidden

Requesting the old chat's transcript; continuing past discrepancies without reconciling with the human; resurrecting items from «Не делать»; starting from scratch when an active HANDOFF exists.

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.

11d ago First seen · 23 lines · 92 tokens per session scan A b1a0f1b638cb

Subscribe to this mod's changes

pf-resume is a skill published in the GitHub repository turvodnik/pf-handoff (6 stars, last pushed 26d ago), licensed MIT. It adds 92 tokens to every session and 542 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.

Claude Code Memory and context agent-skills ai-agents claude context-management context-window

lethe-offload

Use throughout long sessions to keep the context window small — archive large tool outputs to LETHE and recall them on demand, saving tokens.

JesusGarcia9009/lethe-engineering · 32 tokens

kn-init

Use at the start of a new session to read project docs, understand context, and see current state.

knowns-dev/knowns · 23 tokens

kn-extract

Use when extracting reusable patterns, decisions, failures, or knowledge into documentation.

knowns-dev/knowns · 18 tokens

alive:save

The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…

alivecontext/alive · 78 tokens

mnemo-cortex

Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.

GuyMannDude/mnemo-cortex · 44 tokens

alive:session-history

Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…

alivecontext/alive · 76 tokens