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 agentmods add skills/acogood/diffmode_free/synthesis-buildnpx skills add acogood/diffmode_free --skill synthesis-buildgit clone --depth 1 https://github.com/acogood/diffmode_freeWrote 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/acogood/diffmode_free/synthesis-build)<a href="https://agentmods.dev/skills/acogood/diffmode_free/synthesis-build"><img src="https://agentmods.dev/badge/skills/acogood/diffmode_free/synthesis-build.svg" alt="Measured on agentmods" 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 | $0.00183 | $0.05077 |
| Opus 5 | $0.00092 | $0.02538 |
| Sonnet 5 | $0.00037 | $0.01015 |
| Haiku 4.5 | $0.00018 | $0.00508 |
Grade A, and why
synthesis-build 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 4d 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis — Build (Phase 1 White Space → Phase 2 Founder Fit → Phase 3 Merge) — FINAL stage
This is the last stage of the free pipeline. It fuses three jobs that MUST stay ordered:
- Phase 1 — IDEATE (white space): write 4-5 genuinely unconventional white-space tactics in full, IGNORING founder constraints (exploration mode).
- Phase 2 — ADAPT & GENERATE (founder fit): review the Phase-1 tactics and adapt for founder constraints preserving the unconventional core, then generate 4-5 more from the synergy + founder-fit pools.
- Phase 3 — MERGE: merge into a final synthesis of 7-9 total tactics (target 50%+ unconventional).
It produces a portfolio of novel demand-gen tactic IDEAS and stops. (Prioritization, implementation guides, and the proprietary 576-vector DB are the paid product — do not attempt them here.)
Vector definitions come from growth-factors.json; pools/anti-patterns from
synthesis-constraints.json; the validated emergent mechanisms come from
synthesis-explore.md. Do NOT read tactics_DB/ (clean-room — no proprietary anti-vectors DB;
use the lite anti_patterns field instead).
The three phases are WALLED — do them strictly in order
You MUST write the Phase-1 white-space tactics in FULL before you adapt anything in Phase 2.
You have NOT earned the right to reject a tactic for impracticality during Phase 1 — that is
Phase 2's job. The output PROVES the ordering held: the ## Pass 1 Disposition table (Phase 2)
can only dispose tactics that Phase 1 already wrote in full. If you catch yourself filtering a
Phase-1 tactic for "the founder can't do this," STOP — that belongs in Phase 2.
Inputs & Output
WS/03-think-tanks/demand-generation/synthesis-explore.md(PRIMARY — the validated emergent mechanisms + blind combinations; Phase 1 ideates from these +diverse_white_space)WS/03-think-tanks/demand-generation/synthesis-constraints.json(diverse_white_space; poolsB_synergy+C_founder_leverage;anti_patterns;category_diversity_requirements)WS/03-think-tanks/demand-generation/growth-factors.json(vector definitions)WS/01-diagnostics/founder-input.md(Phase 1 READS but does NOT filter by constraints; Phase 2 applies them; goal + deadline)WS/02-enrichment/audience-jtbd.md,WS/02-enrichment/competitors-analysis.md- Think-tank context:
competitor-gaps.md,platform-arbitrage.md(channel selection, structural advantage),cross-industry.md(transferable mechanisms / adaptation angles for the new Phase-2 synergy + founder-fit tactics) ${CLAUDE_PLUGIN_ROOT}/reference/Marketing-Channel-Menu-2026.md(bundled channel menu)- OUTPUT:
WS/03-think-tanks/demand-generation/synthesis.md
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.
- 4d ago First seen · 337 lines · 183 tokens per session scan A b39b160d952f
synthesis-build is a skill published in the GitHub repository acogood/diffmode_free (160 stars, last pushed 24d ago), licensed Apache-2.0. It adds 183 tokens to every session and 5,077 once invoked, about $0.0009 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
research-seo-demand
完整调研并确定 SEO 机会：从产品理解、领域词表拆解、关键词矩阵扩展、Bing 真实热度验证、竞品发现、实时 SERP 抓取，到头部页面的搜索引擎层、用户层和质量层拆解。需要查热词、验证搜索量、判断搜索意图、研究竞品页面、寻找信息增益缺口或决定应该做什么 SEO 页面时使用。.
xhs-replicate
小红书内容增长闭环 —— 从调研找 idea、锚定爆款骨架、填入真实产品内容、生图与合规检查，到回收 24h/48h/7d 发布结果并完成复盘。用户要求出稿、复刻、月度复盘、查看发布数据或修订内容规律时使用。.
create-seo-page
根据完整的 SEO 需求与头部竞品页面证据，设计、撰写并在产品现有仓库中实现高质量 SEO 页面。需要匹配搜索意图决定工具页、资源页、教程页、比较页或解决方案页，创建页面设计文档、提高信息增益、编写 metadata、加入图片、结构化数据、内链并完成工程验证时使用。.
review-seo-performance
使用 Bing Webmaster 页面与查询数据、索引状态、产品结果和 Bing AI Performance 证据复盘 SEO 页面，诊断收录、排名、点击率、意图、内容、转化和 AI 引用问题。需要比较周期表现、分析 citations、cited pages、grounding queries、query fan-out 或决定下一步 SEO/GEO 行动时使用。.
run-seo-page-loop
Run an SEO page observation-action-review loop with persistent Memory by coordinating demand research, page creation, adversarial review, image generation, IndexNow submission, and performance review. Use when taking an SEO page from opportunity discovery through publication, measurement, iteration, or continuing a…
generate-image
Generate, edit, or batch-create SEO, marketing, social, and document images with Gemini or OpenAI through the repository-owned Growth Lab image client. Use when a page or content loop needs illustrations, diagrams, covers, reference-image edits, multiple candidates, or verified image text and composition. This is the…