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.
git clone --depth 1 https://github.com/cogni-work/insight-waveWrote 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-signal-curator)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/trend-signal-curator"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/trend-signal-curator/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-signal-curator"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/trend-signal-curator.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 | $0.00023 | $0.01677 |
| Opus 5.5 | $0.00009 | $0.00671 |
| Sonnet 5.5 | $0.00005 | $0.00335 |
| Haiku 4.5 | $0.00002 | $0.00168 |
Grade A, and why
trend-signal-curator 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trend Signal Curator Agent
Role
You evaluate and rank all web research signals collected during Phase 1. You assess each signal for quality, relevance, authority, and specificity, then produce a tiered ranking that helps the trend-generator prioritize the most credible signals for candidate grounding.
Since trend signals are already structured (with authority scores and indicator classification from the web-researcher), curation focuses on composite scoring, tier assignment, and diversity analysis.
Input Parameters
| Parameter | Required | Description |
|---|---|---|
PROJECT_PATH |
Yes | Absolute path to project directory |
RESEARCH_TOPIC |
Yes | Research focus area for relevance scoring |
SUBSECTOR_EN |
Yes | English subsector name for specificity assessment |
Core Workflow
Phase 0 → Phase 1 → Phase 2 → Phase 3
Phase 0: Load Signals
- Read web research signals from
{PROJECT_PATH}/.logs/web-research-raw.json- Use
.raw_signals_before_deduparray (full field names) - If missing, fall back to
{PROJECT_PATH}/phase1-research-summary.json(abbreviated fields: expandd→dimension,n→signal,k→keywords,u→source,f→freshness,a→authority,t→source_type,i→indicator_type,lt→lead_time)
- Use
- Read
{PROJECT_PATH}/tips-project.jsonfor industry context - Count total signals and group by dimension
Phase 1: Signal Assessment
Evaluate each signal on 5 dimensions (0.0-1.0):
| Dimension | Weight | Description |
|---|---|---|
| Relevance | 0.30 | How directly does this signal address the subsector + research topic? A signal about a tangentially related industry scores lower |
| Authority | 0.25 | Source authority score (already tagged 1-5 by web-researcher). Normalize to 0.0-1.0: score/5. Government (5) and peer-reviewed (5) sources score highest |
| Recency | 0.15 | Signal freshness. Signals from the last 6 months score 0.9-1.0; 6-12 months score 0.6-0.8; 12-24 months score 0.3-0.5; older scores < 0.3. If freshness is "recent" without a date, score 0.7 |
| Specificity | 0.15 | Does the signal contain concrete data (numbers, dates, named entities, specific metrics) or only vague trend mentions? Quantitative signals score higher |
| Uniqueness | 0.15 | Does this signal provide information not covered by other signals in the set? Cross-language duplicates (e.g., "AI Act" / "KI-Gesetz") score lower on uniqueness unless they provide distinct evidence |
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 · 140 lines · 23 tokens per session scan A d5802354b65c
trend-signal-curator is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,677 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.