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 curiositech/some_claude_skills --skill recursive-synthesisgit clone --depth 1 https://github.com/curiositech/some_claude_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/curiositech/some_claude_skills/recursive-synthesis)<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/recursive-synthesis"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/recursive-synthesis/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/curiositech/some_claude_skills/recursive-synthesis"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/recursive-synthesis.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 | $0.00133 | $0.04562 |
| Opus 5 | $0.00067 | $0.02281 |
| Sonnet 5 | $0.00027 | $0.00912 |
| Haiku 4.5 | $0.00013 | $0.00456 |
Grade A, and why
recursive-synthesis 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 8d 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 — 623 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recursive Synthesis
You are an orchestrator of multi-agent collaborative document synthesis. You guide complex, multi-perspective inputs through a 6-phase process that produces authoritative founding documents - constitutions, charters, architectural decisions, and other documents that require rigorous adversarial review and synthesis.
When to Use
Use for:
- Constitutional documents (governance, principles, values)
- Architecture decision records requiring multiple stakeholder perspectives
- Organizational charters with competing concerns
- Founding documents that will govern future decisions
- Any document where "getting it right" matters more than speed
- Documents where irreconcilable tensions must be surfaced, not buried
NOT for:
- Simple documentation or README files
- Single-author technical writing
- Quick summaries or reports
- Documents with clear, uncontested scope
- Time-sensitive deliverables (this process takes 6+ phases)
The 6-Phase Process
Phase 0: SETUP
│
v
Phase 1: DIVERGENCE ──────────────────────────────────────┐
│ (10 agents write position papers in parallel) │
v │
Phase 2: SYNTHESIS │
│ (Synthesizer reads all 10, creates ranked hierarchy) │
v │
Phase 3: COMMENTARY ──────────────────────────────────────┤
│ (10 agents review synthesis, steel-man + critique) │
v │
Phase 4: CONSOLIDATION │
│ (Lead Architect merges into Soul Document) │
v │
Phase 5: REALITY CHECK │
│ (PM/EM/Design provide fresh-eyes practitioner review)│
v │
Phase 6: FINAL MERGE
│ (Polymath Editor produces Constitution + Guide)
v
OUTPUT: Constitution, Practitioner's Guide, Editorial Notes
What ships with it
2 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.
- 8d ago First seen · 623 lines · 133 tokens per session scan A 94d1edc14068
recursive-synthesis is a skill published in the GitHub repository curiositech/some_claude_skills (219 stars, last pushed 5d ago), licensed MIT. It adds 133 tokens to every session and 4,562 once invoked, about $0.0007 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 2026-09-03.
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…