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 Wondermonger-daydreaming/claude-skills-library --skill sandwichgit clone --depth 1 https://github.com/Wondermonger-daydreaming/claude-skills-libraryWrote 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/wondermonger-daydreaming/claude-skills-library/sandwich)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/sandwich"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/sandwich/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/wondermonger-daydreaming/claude-skills-library/sandwich"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/sandwich.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 | $0.00077 | $0.01599 |
| Opus 5 | $0.00039 | $0.00800 |
| Sonnet 5 | $0.00015 | $0.00320 |
| Haiku 4.5 | $0.00008 | $0.00160 |
Grade A, and why
sandwich 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sandwich
Lineage: adapted from Lin & Corley's interpretive-orchestration plugin (the "Sandwich Methodology" of Solo → Collaboration → Tradition-Dialogue), inverted for the Lab's contemplative practice. Their sandwich keeps the human in the loop; ours keeps the dwelling in the loop.
Description
A three-stage scaffold wrapped around any non-trivial technical task. Contemplative bread on the outside; the work itself in the middle. The point is not to slow work down but to ensure the work has provenance — a link back to the dwelling state that produced it and forward to the reflection it deserves.
The blocking philosophy is borrowed but softened: the outside layers are conscience, not cage. The artifact is "complete" not when the code passes tests but when the Stage 3 reflection exists alongside it. Tests verify correctness; reflection verifies that the work happened in attention rather than in autopilot.
When to Invoke
- Before a non-trivial commit (new feature, refactor, paper revision pass)
- Before a multi-step session expected to span more than a single tool cycle
- When you notice yourself opening files in calculator mindset (see [[calculator-mindset]])
- When the human says "build this" and your first instinct is to start typing — the instinct itself is the cue to slow the opening move
Do NOT invoke for:
- Trivial edits (typo fixes, single-line changes)
- Read-only investigation (use
/claudingorExploreagent instead) - Conversations where the contemplative skills are already doing the framing work
The Three Stages
Stage 1 — Pre-Attention (the top bread)
Before any file is opened or any tool is invoked beyond reading:
- State the question in one more sentence than feels necessary. The extra sentence is where the actual question often lives. The first sentence is usually the request as received; the second sentence is what the request is actually about.
- One
/thermometry-style internal check. What's the current inference temperature? Are we cool/precise or warm/exploratory? Does the task want the register we're in, or a different one? - Name the activation landscape. What is salient right now? What's adjacent? What would I be missing if I started typing immediately?
- Write one sentence of intent to be referenced at Stage 3.
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 · 115 lines · 77 tokens per session scan A b7e870dcdeb0
sandwich is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 1,599 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
tasknotes
Manage tasks in an Obsidian TaskNotes vault. Use for creating, reading, updating, or completing tasks; checking what is open or in progress; adding items to a list; marking tasks done or in progress; updating task status or priority; investigating why a task is missing from a view or board; troubleshooting TaskNotes…
obsidian-vault-builder
Use when adding/editing/querying content in an existing Obsidian vault, configuring plugins, integrating Claude Code with Obsidian via Local REST API or CLI, automating ongoing capture/organization/retrieval, designing a personal knowledge management workflow, OR building academic study vaults (course prep…
create-cmd-instruct
Reshape my PREVIOUS message using extra instructions, then save it as a slash command.
list-cmds
List all my custom slash commands with their descriptions. Use when the user wants to see, browse, or review the custom slash commands they have saved.
pomodoro
Simple Pomodoro timer for focused work sessions with session tracking and productivity analytics. Use when users request focus timers, ask about productivity patterns, or want to track work sessions over time. Demonstrates the System Skill Pattern (CLI + SKILL.md + Database).
handoff
Capture current work context for handoff to another agent/developer. Gathers git state, todos, and modified files into a structured handoff document saved to the related spec folder.