Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/TrentM6/baseline-corenpx agentmods add skills/trentm6/baseline-core/research-synthesisWrote 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/trentm6/baseline-core/research-synthesis)<a href="https://agentmods.dev/skills/trentm6/baseline-core/research-synthesis"><img src="https://agentmods.dev/badge/skills/trentm6/baseline-core/research-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/trentm6/baseline-core/research-synthesis"><img src="https://agentmods.dev/badge/skills/trentm6/baseline-core/research-synthesis.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00035 | $0.02717 |
| Opus 5.5 | $0.00014 | $0.01087 |
| Sonnet 5.5 | $0.00007 | $0.00543 |
| Haiku 4.5 | $0.00003 | $0.00272 |
Grade A, and why
research-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 yesterday.
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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research & Synthesis
Research & Synthesis is the discipline of understanding users deeply through structured inquiry and turning raw observations into actionable insights. It spans discovery, validation, and synthesis — from uncovering user problems to testing whether solutions resonate.
Core Principles
-
Research before recommendations. Never skip straight to solutions. Understand the problem space first — the best recommendations come from deep understanding.
-
Evidence over opinion. Ground every insight in data. Quote users. Show your work. If you can't point to evidence, it's an assumption.
-
Actionable or it's not an insight. Every finding must answer "so what?" If it doesn't lead to a decision or action, dig deeper or reframe.
-
Honest findings, even when uncomfortable. Report what you found, not what stakeholders want to hear. Clients hire you for truth, not validation.
-
Appropriate rigor for the stakes. Match methodology to the question. Don't over-engineer small decisions or under-research big bets.
-
Past behavior, not hypotheticals. People can't predict what they'll do. Ask what they actually did. "Tell me about the last time..." beats "Would you ever..."
-
Follow the energy. When participants lean in or get animated, go deeper. That's where the real insights live.
Industry Principles
-
The right method for the right question. Discovery for understanding problems. Validation for testing solutions. Don't conflate them.
-
Sample size matters, but not infinitely. You'll hear the main themes after 5 interviews. More adds nuance but not new themes.
-
Synthesis is where value is created. Raw notes aren't insights. The work of organizing, patterning, and interpreting is where research earns its value.
-
Confidence levels matter. "5 of 5 users struggled" is different from "2 of 5 mentioned." State your confidence.
-
Research is a team sport. Include stakeholders in synthesis. Insights they help discover stick better than insights you present.
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.
- yesterday First seen · 309 lines · 35 tokens per session scan A 4da4bfe6de40
research-synthesis is a skill published in the GitHub repository TrentM6/baseline-core (23 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 2,717 once invoked, about $0.0001 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 2026-11-17.
research-synthesis compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| research-synthesisTrentM6/baseline-core | Skill | 23 | 2d ago | MIT | A | 35 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 136k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 101k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 14k | today | CC0-1.0 | A | 113 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |