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 nicknisi/claude-plugins --skill handoffgit clone --depth 1 https://github.com/nicknisi/claude-pluginsWrote 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/nicknisi/claude-plugins/handoff)<a href="https://agentmods.dev/skills/nicknisi/claude-plugins/handoff"><img src="https://agentmods.dev/badge/skills/nicknisi/claude-plugins/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/nicknisi/claude-plugins/handoff"><img src="https://agentmods.dev/badge/skills/nicknisi/claude-plugins/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00089 | $0.00528 |
| Opus 5.5 | $0.00036 | $0.00211 |
| Sonnet 5.5 | $0.00018 | $0.00106 |
| Haiku 4.5 | $0.00009 | $0.00053 |
Grade A, and why
handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Write a handoff document that lets a fresh agent continue this work without re-deriving any context. Save it to a path produced by f=$(mktemp "${TMPDIR:-/tmp}handoff-XXXXXXXX") && mv "$f" "$f.md" && echo "$f.md" (read the file before you write to it).
If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.
What to capture
The goal is compression, not transcription. A good handoff is under 200 lines and gives the next agent everything it needs to start working immediately.
Include these sections (skip any that don't apply):
Goal — What the user is trying to accomplish, in one or two sentences. Include the "why" if it's not obvious from the task itself.
Current state — Where things stand right now: branch name, what's been built/changed, what works, what doesn't. Be specific — file paths, function names, test results.
Decisions made — Choices that were made during this session and their rationale. The next agent shouldn't re-litigate settled questions.
What failed / dead ends — Approaches that were tried and abandoned, and why. This prevents the next agent from repeating mistakes.
Open questions / blockers — Anything unresolved that needs the user's input or further investigation.
Next steps — Concrete actions for the next session, ordered by priority.
Suggested skills — Include a "suggested skills" section in the document, which suggests skills that the agent should invoke.
What NOT to include
Do not duplicate content already captured in other artifacts — PRDs, plans, ADRs, issues, commits, diffs. Reference them by path or URL instead. The handoff supplements the commit history; it doesn't replace it.
Do not include verbatim code blocks unless they're critical context that isn't committed anywhere (e.g., a snippet the user pasted that informed a design choice).
Do not rehash the full conversation. Distill it.
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.
- 2mo ago First seen · 38 lines · 89 tokens per session scan A 932b1a7f6d66
handoff is a skill published in the GitHub repository nicknisi/claude-plugins (114 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 528 once invoked, about $0.0004 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.
handoff compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| handoffnicknisi/claude-plugins | Skill | 114 | 2mo ago | MIT | A | 89 | Claude Code |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | today | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | today | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 0 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | today | MIT | A | 115 | Claude Code, Codex |