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-explorenpx skills add acogood/diffmode_free --skill synthesis-exploregit clone --depth 1 https://github.com/acogood/diffmode_freeWhat 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 | $0.00178 | $0.05060 |
| Opus 5 | $0.00089 | $0.02530 |
| Sonnet 5 | $0.00036 | $0.01012 |
| Haiku 4.5 | $0.00018 | $0.00506 |
Grade A, and why
synthesis-explore 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 2d 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 — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis — Explore (Phase 1 Blind Combinations → Phase 2 Emergent Mechanisms)
This is the FIRST synthesis stage. It fuses two jobs that MUST stay ordered: Phase 1 draws vector combinations BLIND (vector-first, before any tactic exists), and Phase 2 derives the NOVEL MECHANISM that emerges from each combination. Vector-first thinking is the novelty engine: you commit to combinations BEFORE knowing what tactic they might produce, which is how you escape conventional playbooks. Output: 15-20 raw vector combinations + 12-18 validated mechanisms. NO TACTIC NAMES. NO EXECUTION STEPS. (Tactic design is synthesis-build's job.)
Vectors and their definitions come from the per-run growth-factors.json (the LIGHT DB). Do
NOT read tactics_DB/ (clean-room — moat-critical). The category structure and
{prefix}-NNN-slug ID format are shared conventions; the specific IDs are whatever this run
mined.
The two phases are WALLED — do them strictly in order
You MUST complete Phase 1 (blind draw + combinations) in FULL before starting Phase 2
(mechanisms). The output must physically PROVE this ordering: the section
## Blind Draw (IDs only) must precede ## Vector Combinations, which must precede
## Validated Mechanisms. If you catch yourself deriving a mechanism (Phase 2) before the
blind draw and combinations (Phase 1) are written, STOP — you have broken the wall; go back.
Inputs & Output
The invoker provides (do not hardcode absolute paths):
WS/01-diagnostics/founder-input.mdWS/03-think-tanks/demand-generation/growth-factors.json(LIGHT vector DB — vector IDs, categories, mechanisms, transferability, saturation_risk)WS/03-think-tanks/demand-generation/synthesis-constraints.json(mandatory pools, white space, prohibited combinations, category diversity)WS/02-enrichment/audience-jtbd.md(trigger events + emotions)- Think-tank context (use if present):
WS/03-think-tanks/demand-generation/cross-industry.md(transferable mechanisms worth combining),competitor-gaps.md(open channels/segments),platform-arbitrage.md(emerging-platform timing windows) - OUTPUT:
WS/03-think-tanks/demand-generation/synthesis-explore.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.
- 2d ago First seen · 366 lines · 178 tokens per session scan A f545841a7821
synthesis-explore is a skill published in the GitHub repository acogood/diffmode_free (160 stars, last pushed 22d ago), licensed Apache-2.0. It adds 178 tokens to every session and 5,060 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…