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 acogood/diffmode_free --skill synthesis-exploregit 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-explore)<a href="https://agentmods.dev/skills/acogood/diffmode_free/synthesis-explore"><img src="https://agentmods.dev/badge/skills/acogood/diffmode_free/synthesis-explore/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/acogood/diffmode_free/synthesis-explore"><img src="https://agentmods.dev/badge/skills/acogood/diffmode_free/synthesis-explore.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 | $0.00178 | $0.05060 |
| Opus 5.5 | $0.00071 | $0.02024 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (165 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 178 tokens to every session and 5,060 once invoked, about $0.0007 per session on Opus 5.5. 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
newsjack-detector
Monitor current news and reaction signals, then decide which are credible newsjacking opportunities for a client. Uses the local monitoring engine for evidence, but the skill owns PR judgment, brand safety, standing, decay, angle fit, and handoff.
crisis-holding
Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).
voice-extractor
Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta function-word vector, MATTR lexical diversity, sentence-length burstiness, Biber Dimension-1 register…
fact-check
Extract factual claims from PR copy, verify each claim independently, attach concrete citations, and warn when certainty is low. Runs each claim through proven newsroom verification methods (lateral reading, source-tier climbing, provenance pillars, triangulation, calibrated rating) and puts the burden of proof on the…
find-journalists
Build a researched, fit-checked journalist list for a specific PR campaign. Prefer Medialyst's asynchronous media-list research workflow when available, with explicit approval before credit spend; otherwise produce a best-effort local list without guessed contacts.
press-clip
Turn a live article URL into a press clip that looks like the real coverage — the publication's own logo, fonts, photos and layout kept intact, the ads and clutter removed, and (for a roundup) just the client's section. Renders to PDF. You inspect each site and tailor the removal; the bundled script carries no…