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 ralfyishere/rules-with-receipts --skill human-handoffgit clone --depth 1 https://github.com/ralfyishere/rules-with-receiptsWrote 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/ralfyishere/rules-with-receipts/human-handoff)<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/human-handoff"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/human-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/ralfyishere/rules-with-receipts/human-handoff"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/human-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 | $0.00103 | $0.01296 |
| Opus 5 | $0.00051 | $0.00648 |
| Sonnet 5 | $0.00021 | $0.00259 |
| Haiku 4.5 | $0.00010 | $0.00130 |
Grade A, and why
Human 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 10d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human Handoff
Purpose
When a step needs human hands, the handoff itself is a deliverable — and a badly designed one fails silently: the user does something, believes it worked, and you discover the miss two steps later. The core insight, learned the hard way: humans can't see the system state you'd verify, so your instructions must name the completion signal — what DONE looks like — not just the actions. A browser saying "connected" while the terminal grant never completed is the canonical failure.
When to use this skill
- Any step requiring the user's credentials, browser, approvals, or physical presence.
- Multi-step out-of-band flows you can't observe: device-code auth, account creation, 2FA setup, settings pages.
- A human step that already failed once — the retry needs a redesigned handoff, not the same instructions louder.
When NOT to use this skill
- Steps you can do yourself with available tools — exhaust those first; the best handoff is none (do everything possible, hand over only the irreducible remainder).
- Simple one-click asks with self-evident completion ("merge the PR") — a sentence suffices.
Operating procedure
- Minimize the human surface first. Before writing instructions, take every sub-step you can: prepare the files, pre-fill the values, stage the commands. Hand over only what genuinely requires them.
- Write exact steps with exact values. Field names with the literal strings to paste, which account to be logged into, which button label to click. "Set up trusted publishing" fails; "Owner:
acme-dev, Repository:acme-tool, Workflow:publish.yml, Environment:pypi" succeeds first try. - Name the completion signal explicitly. The single highest-leverage line: tell them what DONE looks like from their seat, and distinguish it from intermediate states that masquerade as done. "Don't close anything until the terminal prints ✓ Authentication complete — the browser saying 'connected' is not the finish line."
- Name the common failure point if the flow has one (the step people skip, the screen that looks final but isn't). One sentence of "this is the part that usually gets missed" beats three retries.
- Verify from your side when they report back. "Done" from the user is a claim, not a state — check the scope list, the API response, the file, whatever you can observe. If it didn't take, diagnose which step broke before re-asking; never resend identical instructions after a failure.
- Batch, don't dribble. If the task needs three human steps, hand over all three with their completion signals at once — round-trips are the expensive resource.
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.
- 10d ago First seen · 62 lines · 0 tokens per session scan A 9456d468e170
Human Handoff is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 1,296 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
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.
frontend-design
A design guide for building polished web interfaces such as pages, dashboards, forms, navigation, and reusable UI components. It covers HTML, CSS, JavaScript, and common frontend frameworks.
alterlab-cobrapy
Build and analyze genome-scale constraint-based metabolic models with COBRApy — flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockouts, flux sampling, and SBML model I/O. Use when simulating metabolic networks, predicting growth or knockout phenotypes, or running systems-biology and…
alterlab-depmap
Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use when identifying cancer-specific genetic vulnerabilities, finding synthetic lethal interactions, checking whether a gene is essential in given cell lines, or…
alterlab-qutip
Simulates open quantum systems with QuTiP, the Quantum Toolbox in Python, solving Lindblad master equations (mesolve), Monte Carlo trajectories (mcsolve), and unitary dynamics (sesolve). Use when studying master-equation or Lindblad dynamics, decoherence, dissipation, quantum optics, cavity QED, or open-system time…