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.
npx skills add tanghong123/claude-replay --skill jdi-handoffgit clone --depth 1 https://github.com/tanghong123/claude-replayWrote 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/tanghong123/claude-replay/jdi-handoff)<a href="https://agentmods.dev/skills/tanghong123/claude-replay/jdi-handoff"><img src="https://agentmods.dev/badge/skills/tanghong123/claude-replay/jdi-handoff/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/tanghong123/claude-replay/jdi-handoff"><img src="https://agentmods.dev/badge/skills/tanghong123/claude-replay/jdi-handoff.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 | $0.00095 | $0.00518 |
| Opus 5 | $0.00048 | $0.00259 |
| Sonnet 5 | $0.00019 | $0.00104 |
| Haiku 4.5 | $0.00010 | $0.00052 |
Grade A, and why
jdi-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 12d 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.
What it actually says
jdi-handoff
Hand the current session to agent-jdi so it continues unattended in the
background. This is the mirror of agent-jdi takeover (which hands a background
run back to a human).
When to use
The user wants to stop babysitting the session and let it finish on its own — "hand this off to jdi", "justdoit", "let jdi take it from here", etc.
How
-
Figure out a short instruction for what remains — ask the user, or summarize the current goal in one line.
-
Run, from inside this session (it finds the session automatically):
agent-jdi handoff <instruction>This spawns a detached watcher and then quits this session. Once the session exits, agent-jdi resumes it unattended and drives the work to completion, retrying on recoverable failures.
For Codex, handoff preserves the current Codex permission context:
read-only,workspace-writewith its exact network setting, ordanger-full-access. Capture happens before the watcher starts or the current session exits. If the current turn's permission policy cannot be read safely, handoff aborts and leaves the interactive session running. Retries and backlog drains reuse the captured policy. No extra Skill flag is required. Claude permission behavior is unchanged.
Do not ask for extra confirmation once the user has asked to hand off — just run the command.
Options
agent-jdi handoff --armed <instruction>— arm the handoff without quitting; the user presses/exitthemselves when ready.agent-jdi handoff --interval <secs> --max-attempts <n> <instruction>— tune the unattended retry loop.
Getting it back
To pull the unattended run back to an interactive session later:
agent-jdi takeover
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.
- 12d ago First seen · 56 lines · 95 tokens per session scan A fe48528d0f22
jdi-handoff is a skill published in the GitHub repository tanghong123/claude-replay (2 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 518 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.
Other skills, from other repositories
ast-grep
Use for ast-grep project setup, rule authoring, rule debugging, and structural search workflows.
skill-installer
Install VT Code skills into /.agents/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo, including private repos.
cmd-analyze
Perform comprehensive codebase analysis and generate reports (usage: /analyze [full|security|performance]).
cmd-command
Run a terminal command (usage: /command [args...]).
cmd-review
Review the current diff or selected files (usage: /review [--last-diff|--target |--file |files...] [--style ]).
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends VT Code's capabilities with specialized knowledge, workflows, or tool integrations.