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.
git clone --depth 1 https://github.com/bengous/claude-code-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/commands/bengous/claude-code-plugins/handover)<a href="https://agentmods.dev/commands/bengous/claude-code-plugins/handover"><img src="https://agentmods.dev/badge/commands/bengous/claude-code-plugins/handover/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/commands/bengous/claude-code-plugins/handover"><img src="https://agentmods.dev/badge/commands/bengous/claude-code-plugins/handover.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 | $0.00010 | $0.00665 |
| Opus 5.5 | $0.00004 | $0.00266 |
| Sonnet 5.5 | $0.00002 | $0.00133 |
| Haiku 4.5 | $0.00001 | $0.00067 |
Grade A, and why
handover 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 2d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handover Document Generator
Generate a self-contained context transfer document that allows a fresh agent to continue this session's work. The receiving agent has no access to this conversation — every reference must be complete and verifiable.
Arguments
Parse $ARGUMENTS for:
- focus-area (optional): Narrow the handover to a specific topic (e.g., "authentication", "database")
- --brief: Produce a short summary instead of the comprehensive document
Step 1: Ground Truth
Verify actual repository state before analyzing the conversation:
git status
git log --oneline -10
git diff --stat HEAD~3..HEAD 2>/dev/null || git diff --stat
Reflect on whether the git state matches your session memory. Note any discrepancies — they indicate uncommitted work, reverted changes, or stale assumptions.
Step 2: Reconstruct the Session
Analyze the conversation to capture: the original goal and underlying motivation, key decisions with rationale and rejected alternatives, implementation sequence and obstacles encountered, implicit knowledge and gotchas discovered, and where work stopped.
Focus on the WHY behind decisions — a fresh agent can read the code to see WHAT exists, but needs the handover to understand WHY it exists.
- Original Goal: What the session set out to accomplish and the underlying motivation
- Key Decisions: Significant choices where alternatives existed, with rationale and what was rejected
- Progress: What was planned, what was completed (with file references like
path/file.ts:123), what remains - Challenges: Obstacles that affected the approach and how they were resolved
- Current State: Modified files, git status, branch, uncommitted changes, environment/dependencies
- Context for Continuation: Implicit knowledge, gotchas, reasoning chains, and user preferences that aren't obvious from the code
- Next Steps: Numbered, specific, actionable (e.g., "Run
bun testto verify auth changes" rather than "Test the 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.
- 2d ago Changed ddb26fe9cde9
- 1mo ago Changed · -3 lines 876cc8a26389
- 1mo ago First seen · 71 lines · 10 tokens per session scan A 948ae8870b3d
handover is a command published in the GitHub repository bengous/claude-code-plugins (5 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 665 once invoked, about $0.0000 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 2026-09-03.
Other commands, from other repositories
plan
Plan n8n Linear ticket implementation.
triage
Triage Linear issue with comprehensive analysis.
visual
Restate a spec, task, diff, or the current topic as a compact markdown visual digest.
adhoc-flow
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
end-isparto
You are the Team Lead. The user has run /end-isparto to wrap up the work session.
compiling-project-guidelines
Compile scattered guideline sources into one scope-aware COMPILED-GUIDELINES.md for other skills and ult-context-generate's Constraints layer. Do NOT use to enforce rules at runtime.