recursive-synthesis

recursive-synthesis is a skill for Claude Code from curiositech/some_claude_skills. It costs 133 tokens per session (4,562 once invoked), scanned A, original, MIT.

A multi-stage method for combining viewpoints from several agents into important shared documents such as charters, constitutions, and architecture decisions.

In plain words
What is it for?
Use it to synthesize complex, multi-perspective decisions where competing concerns must be compared, challenged, consolidated, and merged.
Why use it?
It exposes disagreements and subjects proposals to review before producing a single agreed document.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to synthesize complex, multi-perspective decisions where competing concerns must be compared, challenged, consolidated, and merged.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/curiositech/some_claude_skills/recursive-synthesis
Install

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.

Any agent
npx skills add curiositech/some_claude_skills --skill recursive-synthesis
Clone the repo
git clone --depth 1 https://github.com/curiositech/some_claude_skills

Made for: Claude Code.

Wrote 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.

agentmods badge for recursive-synthesis

README.md
[![agentmods](https://agentmods.dev/badge/skills/curiositech/some_claude_skills/recursive-synthesis/github.svg)](https://agentmods.dev/skills/curiositech/some_claude_skills/recursive-synthesis)
Your own site
<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.

agentmods 80×15 button for recursive-synthesis

Your own site · 80×15
<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>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,562 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash 94d1edc14068, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

.claude/skills/recursive-synthesis/SKILL.md · 623 lines

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

Read the full file on GitHub · 623 lines

Files

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.

Changes

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.

  1. 8d ago First seen · 623 lines · 133 tokens per session scan A 94d1edc14068

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens