Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/robertbagge/claude-sagan-pluginnpx agentmods add skills/robertbagge/claude-sagan-plugin/synthesizeWrote 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/robertbagge/claude-sagan-plugin/synthesize)<a href="https://agentmods.dev/skills/robertbagge/claude-sagan-plugin/synthesize"><img src="https://agentmods.dev/badge/skills/robertbagge/claude-sagan-plugin/synthesize/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/robertbagge/claude-sagan-plugin/synthesize"><img src="https://agentmods.dev/badge/skills/robertbagge/claude-sagan-plugin/synthesize.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 | $0.00057 | $0.04095 |
| Opus 5 | $0.00028 | $0.02048 |
| Sonnet 5 | $0.00011 | $0.00819 |
| Haiku 4.5 | $0.00006 | $0.00409 |
Grade A, and why
synthesize 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 9d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
synthesize
Cut an existing research corpus along one axis and write a synthesis in the shape the reader needs.
/deep-research produces breadth: one file per topic, plus synthesis/general.md covering the whole corpus. /synthesize produces depth on a seam that runs across those topics — what the corpus knows about one question, assembled into one document.
{output_dir}/
├── brief.md
├── research/ # read by this skill, never written
│ └── {topic-slug}.md
└── synthesis/
├── general.md # owned by /deep-research — never write this
└── {axis-slug}.md # written by this skill
Why this matters
Two properties make a synthesis trustworthy, and both are easy to lose:
- Citations survive the trip. Material passes through an extraction agent before it reaches the synthesis. If that agent paraphrases a claim and drops its
[T2]tag, the synthesis inherits an unsourced assertion that reads as sourced. Extraction is a copying job, not a writing job. - Nothing is silently skipped. Every topic file gets an agent, even ones that look unrelated from their one-line summary. A seam that runs across a corpus surfaces in files nobody would have triaged into scope.
This skill is corpus-only. It never runs web searches and never introduces material that isn't already in research/. When the axis needs something the corpus lacks, that goes in the Coverage gaps section — which is the input to the next /deep-research round, not something to paper over.
Modes
The mode determines the document's skeleton. Six in the catalog:
| Mode | For a reader who wants | Skeleton |
|---|---|---|
| Briefing | What the corpus knows about the axis, densely, as a peer | Sub-axes of the topic, 3–6 H2s |
| Recommendation | A call, with the reasoning exposed | Options → Recommendation → Rationale → Risks → What would change this |
| Implementation guide | To build the thing, decision already made | Prerequisites → Sequenced steps → Pitfalls → Checkpoints |
| Comparison | To weigh contenders against criteria | Criteria → Per-option assessment → Trade-offs |
| Primer | To learn the axis from zero | Layered: foundations → mechanics → current state, terms defined on first use |
| Timeline | How the axis got here | Chronological phases, each with what changed and what forced it |
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.
- 9d ago First seen · 254 lines · 57 tokens per session scan A 03e80f60628a
synthesize is a skill published in the GitHub repository robertbagge/claude-sagan-plugin (4 stars, last pushed 23d ago), licensed MIT. It adds 57 tokens to every session and 4,095 once invoked, about $0.0003 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 2026-08-31.
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…