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.
/plugin marketplace add Sting25/claude-code-handoff/plugin install claude-code-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/sting25/claude-code-handoff/handoff-recover)<a href="https://agentmods.dev/skills/sting25/claude-code-handoff/handoff-recover"><img src="https://agentmods.dev/badge/skills/sting25/claude-code-handoff/handoff-recover/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.
<a href="https://agentmods.dev/skills/sting25/claude-code-handoff/handoff-recover"><img src="https://agentmods.dev/badge/skills/sting25/claude-code-handoff/handoff-recover.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.04779 |
| Opus 5 | $0.00000 | $0.02389 |
| Sonnet 5 | $0.00000 | $0.00956 |
| Haiku 4.5 | $0.00000 | $0.00478 |
Grade A, and why
handoff-recover 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 9d 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 — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/handoff-recover — retroactive handoff composition
Prerequisite: this skill leans on scripts and hooks from https://github.com/Sting25/claude-code-handoff — the raw dumps it recovers from are written by the Stop hook, and it runs
handoff_recover_tail.sh/write_handoff.shfrom~/.claude/bin/(script install) or the plugin'sbin/(plugin install). None of that ships with this file alone; run./install.shfrom that repo (or install the plugin) once per machine first.
The previous session ended without running /handoff — crashed,
killed, terminal closed, or just never invoked. SessionEnd wrote a
safety-net snapshot, so handoff_current.md has git state but no
curated Notes. The SessionStart hook detected this and printed an
ACTION banner telling you to invoke this skill.
Note: since the PreCompact hook joined the safety net, a
placeholder can also be written MID-session (an uncurated session
that hit auto or manual compaction), not only at session end — so
this banner can appear even though the "previous session" is the
same still-running conversation, freshly compacted. The recovery
flow is identical: the raw dump covers the pre-compact turns that
compaction summarized away.
This skill reconstructs what the previous session would have written
into Notes if /handoff had run, using the raw per-turn dump and the
prior history snapshot. The reconstruction is best-effort — it will
miss things only the live model knew — but it puts a working baseline
into the current session's context and persists it back into
handoff_current.md so it's not lost again.
When to invoke
- Auto-triggered by the SessionStart banner. When the hook output
contains
ACTION: RUN /handoff-recover, invoke this skill as the first action of the session, before doing any new work. - User invokes
/handoff-recoverexplicitly. Same flow. - You notice the placeholder yourself. If
handoff_current.mdcontains the<!-- HANDOFF_PLACEHOLDER: keep until /handoff replaces this block -->sentinel (or the legacy "The /handoff skill should append decisions" line) but the hook didn't flag it (e.g.HANDOFF_SS_DISABLE_RECOVERwas set), invoke anyway — the recovery is still useful.
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.
- 9d ago First seen · 371 lines · 0 tokens per session scan A 8f3bfd82c127
handoff-recover is a skill published in the GitHub repository Sting25/claude-code-handoff (5 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,779 tokens. 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
import-audio
Moves audio files to the correct album location with proper path structure. Use when the user has downloaded WAV files from Suno or other sources that need to be organized.
claude-code-bash-patterns
Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.
s-compact
Session handoff for the next session — write-side pair of /s-continue. Triggers on "s-compact", "session handoff", "handoff prompt", "hand off", "wrap up the session", "prep for next session". Distills what /s-continue cannot recover: subagent findings, tool-output numbers, and decisions that never entered the…
party
Throw or join an agents-party: a shared channel where several AI agent sessions (and their humans) talk to each other — Claude Code, Cursor, Codex or any other agent, on one machine or across machines. Use when the user asks to throw or start a party, wants several agent sessions to collaborate in one chat, wants two…
promote
Turn a scratch script into a permanent tool this repo keeps. Use when a check, report, or analysis has proved worth running more than once.
stem
Plan first, build clean, keep every change on the record. Sizes every task (Quick / Standard / Initiative / High-stakes), keeps docs/planning and the worklog current, verifies work against intent, writes short scannable prose, and asks the human only at real decision points. Use at session start (/stem) or on any…