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 synthesisengineering/synthesis-skills --skill synthesis-action-sheetgit clone --depth 1 https://github.com/synthesisengineering/synthesis-skillsWrote 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/synthesisengineering/synthesis-skills/synthesis-action-sheet)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-action-sheet"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-action-sheet/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/synthesisengineering/synthesis-skills/synthesis-action-sheet"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-action-sheet.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 | $0.00064 | $0.01355 |
| Opus 5.5 | $0.00026 | $0.00542 |
| Sonnet 5.5 | $0.00013 | $0.00271 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
synthesis-action-sheet 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 today.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Action Sheet
After agents carry out the principal's rulings, what remains is theirs: sends that wait for an approval code, and messages and tasks only they can do. A chat reply that mixes those with what is already done leaves the principal unable to tell what was done, what to approve, what to type and what to send. An action sheet is one self-contained page that answers each, built on the page engine of synthesis-decision-packet. A decision closes when it is made; an action closes when it is done and confirmed, and it can carry forward, so the two are separate pages.
Binding rules
- One page per sitting. Everything the principal must act on goes on one sheet: done for you (folded), approve, do. Two pages split the attention the sheet exists to hold.
- Approval codes never go on the page or in a file. The generator refuses any value holding
approveand a code of the guard's shape (a digit, then five hex characters) and any field named for a code, since a pasted summary holding one would grant a send nobody chose. Codes go in chat, on one line. - The chat after a packet or sheet is exactly three lines: what was done (count and link), the page to open, and the codes line. No lists of items in chat; the sheet holds them.
- Generate from a spec; never hand-author or hand-edit the page. Links are built and tested in the generator, and the page carries the packet's integrity marker.
- Open every generated sheet before handing it over. The packet's permanent defects were found by loading the page, not by reading its source.
- A click is a claim, not proof. After the principal marks a message done, confirm it from the source (Messages
chat.db, WhatsAppChatStorage.sqlite, LinkedIn in the browser, sent mail) before logging it under the daily plan's "On your behalf". Log a row with no readable trace as "principal reports done". - Choosing Agent permits exactly that text to exactly that recipient on that channel, once. Use a guarded send tool where one exists, else computer use. The send guard cannot see computer use, so stop on any difference from the row, and verify afterward from the source.
- Money, security, credentials and identity rows, and rows without exact text, are
agent: never, and their links are never prefilled. The generator refuses a spec that says otherwise. - The paste-back returns marks, Me or Agent and notes;
record_actions.pyfiles them. "Not now" and unmarked rows carry forward by exact id (--successor). A row handed to the agent closes only on the agent's confirmation from the source. - File in the owning project's
resources/artifacts/, never only as a chat artifact. Publishing is an adapter per harness, never the foundation. - Feeds: a decision packet's recorded rulings and the daily plan's items only the principal can do become rows. authoring.md shows the mapping.
What ships with it
14 files 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.
- agents/openai.yaml 349 B
- assets/example-spec.json 3.1 KB
- assets/sheet-template.html 21 KB
- assets/spec-schema.txt 5.6 KB
- references/authoring.md 7.8 KB
- references/background.md 4.1 KB
- references/channels-and-links.md 6.2 KB
- references/filing-and-records.md 8.6 KB
- references/publishing.md 4.7 KB
- scripts/build_sheet.py 29 KB runs code
- scripts/record_actions.py 23 KB runs code
- tests/test_sheet_actions.py 17 KB runs code
- tests/test_sheet_browser.py 13 KB runs code
- tests/test_sheet_build.py 21 KB runs code
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.
- today First seen · 63 lines · 64 tokens per session scan A d7d6ead8de47
synthesis-action-sheet is a skill published in the GitHub repository synthesisengineering/synthesis-skills (23 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 1,355 once invoked, about $0.0003 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 2026-10-21.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…