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 hon454/grimoire --skill create-handoff-promptgit clone --depth 1 https://github.com/hon454/grimoireWrote 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/hon454/grimoire/create-handoff-prompt)<a href="https://agentmods.dev/skills/hon454/grimoire/create-handoff-prompt"><img src="https://agentmods.dev/badge/skills/hon454/grimoire/create-handoff-prompt.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 5.1 | $0.00049 | $0.00543 |
| Opus 5 | $0.00024 | $0.00271 |
| Sonnet 5 | $0.00010 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
create-handoff-prompt 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 8d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Handoff Prompt
Create a prompt the user can paste into another task without requiring access to this conversation.
This is an explicit-invocation workflow. Invoke it as
$create-handoff-prompt, optionally followed by the topic or outcome to
transfer.
Before composing, read ../../references/handoff-composition.md completely and
apply its shared contract.
Select The Scope
- Follow an explicit focus supplied with the invocation.
- If that focus is absent from the conversation or lacks enough source context for an accurate handoff, ask one concise missing-context question and stop.
- With no focus, use the active topic only when it is unambiguous.
- If multiple topics or referents are plausible, ask one concise scope question and stop.
- Exclude unselected topics instead of compressing the whole conversation.
Stay Within The Conversation
Treat the selected conversation as the default source. This is not a research or task-management skill.
- Inspect only artifacts explicitly referenced in the conversation, and only when needed for accuracy.
- Do not automatically explore repositories, browse the web, run tests, inspect tasks, search for a destination, send messages, or navigate between tasks.
- Do not claim the receiving task can see this conversation.
- Do not identify a destination. The user chooses it by pasting the result.
Compose And Output
Compose a self-contained payload under the shared contract. After the payload is
complete, let M be the longest run of consecutive backticks anywhere in it
(0 when none), and set the outer fence length to N = max(4, M + 1).
Return exactly one outer fenced code block:
- Start at column 1 with exactly
Nbackticks followed immediately bymarkdownand nothing else. - Put the unchanged payload on the following lines. Preserve every internal backtick or tilde fence literally.
- Close on the line after the payload with exactly
Nbackticks and nothing else.
Use backticks, never tildes, for the outer fence. Write nothing outside it. Do not save a file or write to the clipboard.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 61 lines · 49 tokens per session scan A 56cab58d78c4
create-handoff-prompt is a skill published in the GitHub repository hon454/grimoire (2 stars, last pushed 20d ago), licensed MIT. It adds 49 tokens to every session and 543 once invoked, about $0.0002 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
.codex
Skill ".codex" from knitli/toolshed, covering context hygiene skill, name, description, instructions and 1. discovery.
knowledge-gravity-lab
Analyze folders of Markdown/text research notes, Obsidian vaults, paper cards, invention notes, or memory exports as a practical knowledge map. Use when asked to find center topics, noisy or low-signal notes, possible contamination, overgrown topic groups, orphan notes, cleanup actions, or a useful public…
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
claude-compaction-restore
Use when a Claude Code session has just compacted, is about to compact, reached context limit, resumed after /compact, or needs to rebuild its working mental model from Claude JSONL transcripts and touched files.
agentic-os
A design for running persistent specialist agents, commands, scripts, and file-based memory inside Codex. It keeps the setup in project files so it can continue across sessions.