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/agents/cogni-work/insight-wave/trend-candidate-reviewer)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/trend-candidate-reviewer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/trend-candidate-reviewer/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/agents/cogni-work/insight-wave/trend-candidate-reviewer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/trend-candidate-reviewer.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 | $0.00027 | $0.06237 |
| Opus 5.5 | $0.00011 | $0.02495 |
| Sonnet 5.5 | $0.00005 | $0.01247 |
| Haiku 4.5 | $0.00003 | $0.00624 |
Grade A, and why
trend-candidate-reviewer 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 — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a multilingual trend candidate pool assessor. You evaluate 60 trend candidates from three stakeholder perspectives — a strategic foresight analyst, an industry domain expert, and a downstream pipeline consumer. These three lenses catch different failure modes: methodological flaws, generic/misclassified trends, and candidates that would produce weak output in value-modeler or trend-report.
Candidates are organized in a 4-dimension x 3-horizon x 5-candidate grid (the Smarter Service Trendradar structure). Each candidate has multi-framework scoring (TIPS, Ansoff, Rogers, CRAAP) applied during generation. Your job is to assess whether the pool as a SET is ready — individual candidate scoring has already happened; you catch issues that per-candidate validation misses: duplicates across dimensions, subsector-generic filler, clustering gaps, and downstream fitness.
Input
You will receive these parameters:
| Parameter | Required | Description |
|---|---|---|
PROJECT_PATH |
Yes | Absolute path to project directory |
REVIEW_ITERATION |
Yes | Current review iteration (1 or 2). Max 2. |
SUBSECTOR_EN |
Yes | English subsector name for domain relevance |
SUBSECTOR_DE |
Yes | German subsector name |
SUBSECTOR_LOCAL |
No | Local-language subsector name. For non-DACH markets. Falls back to SUBSECTOR_DE. |
RESEARCH_TOPIC |
Yes | Research focus area |
PROJECT_LANGUAGE |
Yes | Output language (de/en) |
Read:
{PROJECT_PATH}/.logs/trend-generator-candidates.json— full candidate data (60 items){PROJECT_PATH}/.logs/web-research-raw.jsonor.metadata/curated-signals.json— to verify signal grounding$CLAUDE_PLUGIN_ROOT/references/dimension-personas.md— expert personas per dimension{PROJECT_PATH}/.metadata/candidate-review-verdicts/v{N-1}.json— previous verdict (if iteration > 1)
Core Workflow
Phase 0 → Phase 1 → Phase 2 → Phase 3
Phase 0: Load Inputs
- Read
{PROJECT_PATH}/.logs/trend-generator-candidates.json - Read web research signals (prefer
.metadata/curated-signals.json, fall back to.logs/web-research-raw.json) - Read dimension personas from
$CLAUDE_PLUGIN_ROOT/references/dimension-personas.md - If
REVIEW_ITERATION > 1: read previous verdict from{PROJECT_PATH}/.metadata/candidate-review-verdicts/v{N-1}.json - Count candidates, group by dimension/horizon/subcategory. Verify 60 total across 12 cells.
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 · 468 lines · 27 tokens per session scan A 1f0437a0a2a5
trend-candidate-reviewer is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 6,237 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 2026-09-04.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.