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 bendrucker/claude --skill handoffgit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/bendrucker/claude/handoff)<a href="https://agentmods.dev/skills/bendrucker/claude/handoff"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/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/bendrucker/claude/handoff"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 20 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00087 | $0.01284 |
| Opus 5.5 | $0.00035 | $0.00514 |
| Sonnet 5.5 | $0.00017 | $0.00257 |
| Haiku 4.5 | $0.00009 | $0.00128 |
Grade A, and why
agents: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 21d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Hand the current work to a fresh background agent seeded with a summary of this conversation. The agent starts immediately in the current directory and returns control, so you can walk away and check on it later. Nothing is written to disk: the summary becomes the new agent's opening prompt. When the work is well-scoped and the user wants to step away or parallelize, offer the handoff.
Write the Summary
Synthesize the conversation into a prompt that lets an agent with zero prior context resume without asking questions. Cover:
- Goal: what the work is trying to achieve, in one or two sentences.
- State: what is done, what is in progress, what is untouched.
- Decisions: choices already made and the reasoning, so the agent does not relitigate them.
- Next steps: the concrete actions to take, in order.
- Anchors: the branch, PR, issue, plan doc, or key files by path or URL. Point at these rather than restating them.
- Suggested skills: a short list of skills the agent should invoke for this work (e.g.
pull-request:create,code-review, a project skill). This is the biggest lever on whether the agent picks up your conventions. - Constraints: anything that would surprise a fresh agent, such as test commands, gotchas, or things not to touch.
Keep it dense and specific. If the user passed an argument, treat it as the focus for the next session and shape the summary around it. With no argument, summarize the conversation as a whole.
Redact
The summary becomes the agent's prompt, so strip anything sensitive before launching: API keys, tokens, passwords, connection strings, PII. Reference where a secret lives (an env var, a secrets manager) rather than its value.
Size the Run
The agent runs unattended, so choose its horsepower and autonomy up front. Propose all three to the user with the launch command and your reasoning, and let them override.
Model and Effort
Match --model and --effort to the task. A well-specified, mechanical task runs fine on --model sonnet at --effort medium. Reserve --model opus with --effort high (or xhigh/max) for open-ended, high-stakes, or reasoning-heavy work. --effort takes low, medium, high, xhigh, or max. --model takes an alias (opus, sonnet, haiku, fable) or a full model name.
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.
- 21d ago Changed a14879b5e627
- 1mo ago Changed · -2 tokens per session 4416b07d0a9d
- 2mo ago Changed · +1 lines b157e09a2013
- 2mo ago First seen · 75 lines · 89 tokens per session scan A da4604187ccb
agents:handoff is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 1,284 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
agents:handoff compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agents:handoffbendrucker/claude | Skill | 18 | today | MIT | A | 87 | Claude Code |
| reviewSethGammon/Citadel | Skill | 928 | 4d ago | MIT | A | 17 | Claude Code |
| system-upgradealivecontext/alive | Skill | 132 | yesterday | MIT | A | 55 | Claude Code |
| wenlan-handoffwenlan-app/wenlan | Skill | 94 | today | Apache-2.0 | A | 43 | Claude Code, Codex |
| extract-resumesuxrobGM/jobpilot | Skill | 111 | today | MIT | A | 32 | Claude Code |
| pr-reviewnitinjain999/platform-skills | Skill | 71 | yesterday | Apache-2.0 | A | 81 | Claude Code |
| read-literaturefirecrawl/firecrawl-claude-plugin | Skill | 258 | 3d ago | MIT | A | 101 | Claude Code |