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-reader-briefinggit 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-reader-briefing)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-reader-briefing"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-reader-briefing/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-reader-briefing"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-reader-briefing.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 | $0.00117 | $0.03075 |
| Opus 5 | $0.00059 | $0.01537 |
| Sonnet 5 | $0.00023 | $0.00615 |
| Haiku 4.5 | $0.00012 | $0.00308 |
Grade A, and why
synthesis-reader-briefing 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reader Briefing
A pre-writing discipline for public articles. The briefing is a short structured document, written before drafting begins, that establishes who the article is for and what they bring to the page. It is the audit anchor that the rest of the writing process compares against.
This skill is foundation infrastructure. Other writing skills (synthesis-article-writing, synthesis-article-refresh, the various backdated- and refresh-style skills) treat a committed briefing as a hard precondition: without one, they refuse to proceed.
Why this skill exists
AI-assisted writing has a specific failure mode: when source material (lessons, project context, commit messages, codebases) is loaded into the writing process, the draft inherits the source's framing. The source was written by the writer for the writer. It assumes its reader already has the context. An article written for a stranger has to assume the opposite. Translating between those frames is the actual writing work, and it is the work AI is most likely to skip when given source material to follow.
The result is insider context collapse — right vocabulary deployed for an audience that does not share the writer's context. The grammar is clean, the saturated AI vocabulary is absent, the mechanical quality checks pass, and the article is unreadable to the people it is for.
The fix is procedural: a structured briefing before drafting, then an audit pass against the briefing during review. The check has to be procedural because the writer is the insider — the jargon reads as natural prose to the person who wrote it. Reading the draft and trusting your judgment will not catch this.
This skill is also the procedural workaround for the well-known curse-of-knowledge bias in writing: experts cannot easily imagine what it is like to not know what they know. The briefing forces the imagination.
When to apply
- Any public-facing article, blog post, or essay where the reader is not assumed to share the writer's project context.
- Any documentation written for an external audience (open-source contributors, customers, prospective users).
- Any post that draws from internal lessons, project files, commit messages, or codebases as source material. The risk is highest when source material is rich and the writer is AI-assisted.
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.
- 10d ago First seen · 189 lines · 117 tokens per session scan A 19970176e19f
synthesis-reader-briefing is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed today), licensed Apache-2.0. It adds 117 tokens to every session and 3,075 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…
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…