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-decision-packetgit 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-decision-packet)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-decision-packet"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-decision-packet/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-decision-packet"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-decision-packet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00123 | $0.02427 |
| Opus 5 | $0.00062 | $0.01213 |
| Sonnet 5 | $0.00025 | $0.00485 |
| Haiku 4.5 | $0.00012 | $0.00243 |
Grade A, and why
synthesis-decision-packet 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 12d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Packet
Version 1.1.0 (2026-08-29)
An agent that has analysed N items needs N decisions from its principal. Every default shape fails at scale, and the measurement that produced this skill is blunt: 26 rounds of per-item conversation produced 0 of 30 decisions. One packet produced 30 of 30, in one pass, in one paste.
| Shape | Why it fails |
|---|---|
| One question per turn | N round-trips. This is what cost 26 rounds. |
| One long prose report | The principal holds thirty judgments in their head, keeps their place, and composes a reply that re-identifies each item. |
| A table in chat | Readable, not operable. Nowhere to record a decision, no state if they stop halfway. |
| A form that submits somewhere | Needs a backend, and the reply still has to get back to the agent. |
The failure is not that the principal lacks information. The medium collects no structure, so the burden of structuring the response falls on the person, every time, for every item.
The property to preserve above all others: the principal's cost scales with the number of sittings, not the number of items.
When to use it
Load when you owe your principal five or more parallel decisions of the same shape, each needing supporting context, where you have a defensible recommendation per item and the decisions matter enough to deserve attention but are too numerous for per-item conversation.
Natural fits: review findings to fix or waive · dependency bumps to take or hold · drafts to publish, edit, or kill · files to migrate or leave · flaky tests to quarantine or fix · features to build now, later, or never · candidates to advance on a defined rubric.
When NOT to use it
- Fewer than about five decisions. Just ask in chat. The generator refuses below five without
--allow-small. - The decisions are not parallel in shape. A packet of unlike questions is a form, and a form is worse than a conversation.
- You have no recommendation per item. Then the packet is a questionnaire and your analysis is not finished. Do the analysis. The generator refuses a packet where no row carries a recommendation.
What ships with it
4 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.
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.
- 12d ago First seen · 184 lines · 123 tokens per session scan A 8df3825ace00
synthesis-decision-packet is a skill published in the GitHub repository synthesisengineering/synthesis-skills (19 stars, last pushed today), licensed Apache-2.0. It adds 123 tokens to every session and 2,427 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…