Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add cogni-work/insight-wave/plugin install cogni-trendsWrote 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/cogni-work/insight-wave/trend-research)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/trend-research"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/trend-research/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/cogni-work/insight-wave/trend-research"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/trend-research.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 | $0.00237 | $0.05723 |
| Opus 5.5 | $0.00095 | $0.02289 |
| Sonnet 5.5 | $0.00047 | $0.01145 |
| Haiku 4.5 | $0.00024 | $0.00572 |
Grade A, and why
trend-research 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 — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trend Research
Research groundwork for the TIPS trend pipeline. Reads agreed trend-scout candidates, optionally deep-researches 3–5 high-value Act-horizon trends, dispatches 4 parallel agents (one per Smarter Service dimension) to enrich every candidate with web-sourced quantitative evidence and extract claims, then writes a single research manifest that downstream synthesis and booklet skills consume as their gate.
Purpose
Produce the canonical research artefacts that both the TIPS report (/trend-synthesis) and the comprehensive TIPS catalog (/trend-booklet) need:
- Validate prerequisites (trend-scout
agreed, value-model with investment themes) - Select 3–5 high-value Act-horizon trends for optional deep research
- Enrich each of the ~60 candidates with quantitative evidence and source citations via 4 parallel
cogni-trends:trend-report-writeragents - Extract per-trend claims for downstream verification
- Write
.metadata/trend-research-output.json— the single manifest both/trend-synthesisand/trend-bookletgate on - Auto-recommend
/trend-synthesis(canonical TIPS report) and/trend-booklet(full candidate catalog)
This skill does not write the final report — prose composition lives in /trend-synthesis. Splitting research from synthesis lets the user re-run either stage independently and lets the booklet skill consume the same evidence pool without duplicating work.
Language Support
Full German and English support. This skill follows the shared language resolution pattern — see $CLAUDE_PLUGIN_ROOT/references/language-resolution.md.
Two language concepts:
- Interaction language — how the skill communicates with the user (prompts, status). Determined by workspace
.workspace-config.jsonlanguage setting. - Output language — what language the enriched evidence and claims are written in. Default priority: (1) trend-scout
project_language, (2) workspace language, (3)en. Always confirm at the start of Phase 0.
What ships with it
9 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.
- evals/evals.json 7.7 KB
- references/claims-format.md 3.8 KB
- references/deep-research-selection.md 3.4 KB
- references/evidence-enrichment.md 7.4 KB
- references/i18n/labels-de.md 2.5 KB
- references/i18n/labels-en.md 2.6 KB
- references/region-authority-sources.json 15 KB
- references/research-manifest-schema.md 7.4 KB
- scripts/validate-enriched-trends.sh 3.9 KB runs code
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 · 464 lines · 237 tokens per session scan A aeb1937a5c3a
trend-research is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 237 tokens to every session and 5,723 once invoked, about $0.0009 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 2026-09-04.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…