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 agentmods add skills/everywan-dev/claude-code-engineering/write-a-handover-that-worksnpx skills add everywan-dev/claude-code-engineering --skill write-a-handover-that-worksgit clone --depth 1 https://github.com/everywan-dev/claude-code-engineeringWrote 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/everywan-dev/claude-code-engineering/write-a-handover-that-works)<a href="https://agentmods.dev/skills/everywan-dev/claude-code-engineering/write-a-handover-that-works"><img src="https://agentmods.dev/badge/skills/everywan-dev/claude-code-engineering/write-a-handover-that-works.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.01781 |
| Opus 5 | $0.00026 | $0.00890 |
| Sonnet 5 | $0.00010 | $0.00356 |
| Haiku 4.5 | $0.00005 | $0.00178 |
Grade A, and why
write-a-handover-that-works 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 3d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write a handover that works
The next session starts blind. It gets your files and none of your head. Whatever you did not write down was not saved — it was forgotten, in a way that looks exactly like it never happened.
So the handoff has one job:
Let the next session act without re-deriving anything, and without trusting anything you did not check.
Those are two separate promises. Most handoffs keep the first and quietly break the second.
When to use this
- A task will not finish before the session ends
- You are stopping mid-sequence — applied, not yet verified
- Someone else is picking this up
- You are about to hit a context limit and the work is long
The five sections
Everything else is optional. These five are not.
1. Starting state — captured, not remembered
The output you took before you touched anything: the process list, the version in use, the row count, the routing table. Raw, pasted.
This is not for the change. It is for the argument three days later about whether the change caused the thing that broke. Without it, that argument has no winner.
2. Verified — each claim with the check and its output
One line per claim, and each line carries the command and what it printed.
- New route answers on all three nodes — `<per-node request>` → 200, body contains the new build id (pasted below)
If you cannot attach an output, the claim does not belong in this section. Move it down one.
3. NOT verified — the section everyone skips
🔴 This is the most important part of the handoff and it is the one that gets left out. It is also the only section whose absence is invisible: a handoff with no "not verified" list reads like a handoff where everything was checked.
Every claim you believe but did not observe goes here, with how to check it:
- I believe the workers reconnected after the restart — not observed.
Check: enqueue one job and read the consumer's own log line.
An empty "not verified" section is a claim in itself, and it is almost always false. If yours is empty, you have not sorted the list yet.
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.
- 3d ago First seen · 191 lines · 52 tokens per session scan A d7a6453d485a
write-a-handover-that-works is a skill published in the GitHub repository everywan-dev/claude-code-engineering (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,781 once invoked, about $0.0003 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
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…
pairing
Build work collaboratively in reviewable pieces, handing each piece back for review before starting the next, so the person stays in the lead and steers while the work happens instead of reviewing a finished result. Use when someone says to pair with them on something, asks to collaborate rather than direct, wants to…
memory-notes
How to write well-structured Basic Memory notes: frontmatter, observations with semantic categories, relations with wiki-links, and best practices for building a rich knowledge graph. Use when creating or improving notes.
memory-onboarding
Guide someone new to Basic Memory through designing and building a complete personal knowledge system — interview them about what they want to track, propose a structure, build it with schemas and instruction notes, teach them to use it, and set up their AI assistant to load it automatically. Use this skill whenever a…
basic-memory
Use the Basic Memory knowledge graph for persistent memory across sessions. Search before answering; capture decisions, meetings, and insights as notes.
memory-ingest
Process unstructured external input (meeting transcripts, conversation logs, pasted documents) into structured Basic Memory entities. Extracts entities, searches for existing matches, proposes new entities with approval, creates notes with observations and relations, and captures action items.