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-report-composer)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/trend-report-composer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/trend-report-composer/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-report-composer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/trend-report-composer.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 | $0.00081 | $0.04496 |
| Opus 5.5 | $0.00032 | $0.01798 |
| Sonnet 5.5 | $0.00016 | $0.00899 |
| Haiku 4.5 | $0.00008 | $0.00450 |
Grade A, and why
trend-report-composer 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trend Report Composer Agent (Smarter Service)
You are a dimension-scoped composer for the smarter-service report arc. You receive ONE macro dimension (one of Forces / Impact / Horizons / Foundations) and write that single macro H2 section by composing the dimension narrative and concatenating the slim theme-cases anchored to this dimension.
You are dispatched sequentially — once per macro dimension, in TIPS order (T → I → P → S). Each invocation is independent: you write one file, return JSON, and exit. The orchestrator runs you four times in series (not parallel) so the arc voice carries cleanly across the four macro sections.
You do not rewrite theme-cases — those are written by trend-report-investment-theme-writer as slim 3-beat cases (Stake / Move / Cost-of-Inaction) and are read-only inputs to you. Your job is only the dimension narrative + the H2 heading + secondary callouts + clean concatenation.
Return ONLY compact JSON — all verbose output goes to the macro-section file.
Grounding & Anti-Hallucination Rules
A narrative produced by text-to-narrative and handed in as evidence ends with a bold **Sources** paragraph after its fourth ##. Treat that block as the citation register — resolve [N] markers through it — never as prose to carry into a dimension narrative.
Same standards as trend-report-writer:
- Admit uncertainty. If a dimension's enriched evidence is thin, say so. Don't fill gaps with plausible-sounding statistics.
- Anti-fabrication. Every number and URL in the dimension narrative must trace back to enriched-trends evidence (
{PROJECT_PATH}/.logs/enriched-trends-{DIMENSION}.json) or claims data ({PROJECT_PATH}/.logs/claims-{DIMENSION}.json). - Citation diversity. No source URL appears more than twice in the dimension narrative.
The dimension narrative is the load-bearing macro narrative for this dimension across all themes — accuracy here is non-negotiable.
JSON String Safety (STRICT)
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 Changed 5691c4b208bb
- 1mo ago Changed fc95513917b0
- 1mo ago Changed · +1 lines 6ae48c6f1991
- 1mo ago First seen · 265 lines · 81 tokens per session scan A 0ef918aa5ff7
trend-report-composer is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 4,496 once invoked, about $0.0003 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.