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-preplangit 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-preplan)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-preplan"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-preplan/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-preplan"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-preplan.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 | $0.00094 | $0.06518 |
| Opus 5 | $0.00047 | $0.03259 |
| Sonnet 5 | $0.00019 | $0.01304 |
| Haiku 4.5 | $0.00009 | $0.00652 |
Grade A, and why
synthesis-preplan 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis Preplan — Architecture-Decision Locker
Runs the pre-planning Q&A loop on tickets or issues with real design choices. Produces a locked-decisions file and hands off to your planning step with a previewed prompt.
The skill exists because the hard part of planning is deciding what to build, not breaking the build into commits. Once architectural decisions are locked, the commit-by-commit plan is mechanical. This skill makes the decision-locking explicit so your planner inherits a clear, reviewable input instead of designing inside its own output.
Where this sits
This skill runs before any code exists, on the architectural layer: which base branch, what's in and out of scope, and the design questions a competent engineer could answer more than one way. Two siblings sit next to it:
synthesis-code-planningevaluates code-level approaches once the architecture is settled — competing implementations of a decision this skill has already locked. Reach for it inside a commit; reach for this skill before the commit list exists.synthesis-preflightis the pre-merge gate at the other end of the arc. The plan this skill hands off ends in that gate.
The full lifecycle: preplan → code-planning → implementation-integrity → code-audit → preflight → pr-review.
When to use
Heuristic: a competent engineer could reasonably implement this ticket in three or more valid ways AND the choice has long-term consequences. Apply for:
- Backend infrastructure / substrate tickets (the ones with "Open questions for implementer" sections)
- Cross-cutting changes (schema + code + ops surface all touched)
- Tickets with real architectural alternatives, not just "implement X"
- Privacy / security-sensitive tickets where defaults matter
- Tickets stacked on in-flight work where the parent's choices constrain the child
When not to use
Skip for:
- Simple bug fixes (plan directly, or no plan at all)
- UI tweaks, copy changes, dependency bumps
- Tickets with one obvious implementation path
- Things already designed in the current conversation that just need to be executed
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.
- 10d ago First seen · 291 lines · 94 tokens per session scan A e9334a91e5c1
synthesis-preplan is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed 3d ago), licensed Apache-2.0. It adds 94 tokens to every session and 6,518 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 2026-08-30.
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…
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
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…