replay

replay is a skill for Claude Code from cukas/remembrall. It costs 37 tokens per session (2,091 once invoked), scanned A, original, MIT.

A tool for resuming work from a previous coding session by checking its handoff notes, files, and Git state, then restoring saved patches. A handoff is a written record of unfinished work left for the next session.

In plain words
What is it for?
Use it when taking over interrupted work, restoring a previous session's changes, checking available handoffs, and confirming the repository is ready to continue.
Why use it?
It reduces the risk of continuing from outdated notes or losing unfinished code. The state checks help the agent understand what changed before presenting a briefing.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the remembrall plugin — 6 skills, 12 commands, 4 hooks shipped together

Good fit Use it when taking over interrupted work, restoring a previous session's changes…

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add cukas/remembrall
Claude Code
/plugin install remembrall

Made for: Claude Code.

Or install remembrall, the plugin that ships this one along with the rest of its 6 skills, 12 commands, 4 hooks.

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 replay

README.md
[![agentmods](https://agentmods.dev/badge/skills/cukas/remembrall/replay.svg)](https://agentmods.dev/skills/cukas/remembrall/replay)
Your own site
<a href="https://agentmods.dev/skills/cukas/remembrall/replay"><img src="https://agentmods.dev/badge/skills/cukas/remembrall/replay.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,091 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.02091
Opus 5 $0.00018 $0.01045
Sonnet 5 $0.00007 $0.00418
Haiku 4.5 $0.00004 $0.00209

Measured 7d ago against content hash 4a4380a5b56c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

replay 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 7d 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/replay/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Replay From Handoff

Pick up work from a previous session with full state verification and git patch restore.

Lifecycle

The handoff file is a single-use baton. Read it, verify state, restore patches, delete it.

Steps

  1. Find handoff files — Search both personal and team directories. Check for own session's handoff first:

    REMEMBRALL_ROOT="${CLAUDE_PLUGIN_ROOT:-$(cat /tmp/remembrall-meta/plugin-root 2>/dev/null)}"
    source "${REMEMBRALL_ROOT}/hooks/lib.sh"
    CWD=$(pwd)
    HANDOFF_DIR=$(remembrall_handoff_dir "$CWD")
    TEAM_DIR=$(remembrall_team_handoff_dir "$CWD")
    FALLBACK_DIRS=""
    # Session ID: env var or published by hook
    OWN_SID="${CLAUDE_SESSION_ID:-$(remembrall_read_session_id "$CWD" 2>/dev/null)}"
    echo "Personal: $HANDOFF_DIR"
    echo "Team: $TEAM_DIR"
    echo "Own session: $OWN_SID"
    # Check own session first
    if [ -n "$OWN_SID" ] && [ -f "$HANDOFF_DIR/handoff-${OWN_SID}.md" ]; then
      echo "OWN SESSION HANDOFF: $HANDOFF_DIR/handoff-${OWN_SID}.md"
    fi
    # List all available
    ls -lt "$HANDOFF_DIR"/handoff-*.md "$TEAM_DIR"/handoff-*.md 2>/dev/null || echo "No handoffs found"
    # Fallback: hash lookup missed (path bug, symlink path, or running /replay from a parent dir)
    if ! compgen -G "$HANDOFF_DIR/handoff-*.md" >/dev/null; then
      FALLBACK_DIRS=$(remembrall_replay_fallback_dirs "$CWD" 2>/dev/null || true)
      if [ -n "$FALLBACK_DIRS" ]; then
        echo "Fallback dirs:"
        printf '%s\n' "$FALLBACK_DIRS"
        HANDOFF_DIR=$(printf '%s\n' "$FALLBACK_DIRS" | head -1)
        TEAM_DIR="$HANDOFF_DIR"
        if [ -n "$OWN_SID" ] && [ -f "$HANDOFF_DIR/handoff-${OWN_SID}.md" ]; then
          echo "OWN SESSION HANDOFF (fallback): $HANDOFF_DIR/handoff-${OWN_SID}.md"
        fi
        ls -lt "$HANDOFF_DIR"/handoff-*.md 2>/dev/null || true
      fi
    fi
    
    • 0 files: Tell the user: "No handoff found. Nothing to replay."
    • Own session file found: Use it directly.
    • No exact hash match, one fallback dir: Use that directory and repeat the own-session check there.
    • No exact hash match, multiple fallback dirs: List the newest handoff from each matching directory and ask the user which project/session to replay.
    • Only other sessions' files: List them with timestamps. Ask the user which one to replay before consuming — these belong to other Claude instances.
    • Multiple including own: Use own session's handoff, mention others exist.

Read the full file on GitHub · 156 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. 7d ago First seen · 156 lines · 37 tokens per session scan A 4a4380a5b56c

Subscribe to this mod's changes

replay is a skill published in the GitHub repository cukas/remembrall (6 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 2,091 once invoked, about $0.0002 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

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

alive:capture-context

Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks…

alivecontext/alive · 74 tokens

alive:load-context

The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…

alivecontext/alive · 81 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

alive:mine-for-context

Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…

alivecontext/alive · 63 tokens

alive:my-context-graph

Render an interactive map of your world. Generates the world index from all walnut and bundle frontmatter, then produces a force-directed graph showing connections between walnuts, people, bundles, and tags. Opens in the browser.

alivecontext/alive · 50 tokens