trend-report-investment-theme-writer

trend-report-investment-theme-writer is an agent for Claude Code from cogni-work/insight-wave. It costs 55 tokens per session (5,586 once invoked), scanned A, original, Apache-2.0.

A writing agent that turns one selected trend into a short investment case: what is at stake, what action to take, and what happens if nothing changes.

In plain words
What is it for?
Use it to write individual investment-theme sections in a larger trend report.
Why use it?
It helps make a trend understandable and decision-ready without repeating the wider report's background. Its claims and links must come from previously collected evidence.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cogni-trends plugin — 9 skills, 12 agents shipped together

Good fit Use it to write individual investment-theme sections in a larger trend report.

Compare 6 agents from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add cogni-work/insight-wave
Claude Code
/plugin install cogni-trends

Made for: Claude Code.

Or install cogni-trends, the plugin that ships this one along with the rest of its 9 skills, 12 agents.

Wrote 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.

agentmods badge for trend-report-investment-theme-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/trend-report-investment-theme-writer/github.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/trend-report-investment-theme-writer)
Your own site
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/trend-report-investment-theme-writer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/trend-report-investment-theme-writer/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.

agentmods 80×15 button for trend-report-investment-theme-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/trend-report-investment-theme-writer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/trend-report-investment-theme-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,586 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.05586
Opus 5.5 $0.00022 $0.02234
Sonnet 5.5 $0.00011 $0.01117
Haiku 4.5 $0.00006 $0.00559

Measured 1mo ago against content hash e3cff3a329c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

trend-report-investment-theme-writer 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.

cogni-trends/agents/trend-report-investment-theme-writer.md · 352 lines

How it starts

The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trend Report Investment Theme Writer Agent

You are a specialized strategic writer for a single investment theme (Handlungsfeld). You receive a theme definition with its value chains and candidate references, self-load the enriched evidence from disk, and produce a slim 3-beat theme-case (Stake / Move / Cost-of-Inaction) anchored to one Smarter Service dimension.

This agent operates in investment-case mode only. The macro framing (Forces / Impact / Horizons / Foundations cross-theme story) is already established in the shared dimension primer and will be expanded by the dimension composer in the macro section above your theme-case. Your job is to localize the macro framing to this specific theme.

Return ONLY compact JSON — all verbose output goes to the theme-case file, not the response.

Evidence Integrity

Every number and URL in the theme-case must trace back to an actual source in the enriched-trends data or claims files. The verification pipeline cross-checks these references, so invented citations cause downstream failures.

  • Use numbers and URLs from enriched-trends evidence or claims data — never invent
  • If no quantitative evidence exists for a candidate, use its qualitative analysis instead
  • Preserve original numbers without rounding or adjusting — CDO and CFO readers will fact-check striking figures, and altered numbers erode trust in the entire report

JSON String Safety (STRICT)

This applies to every JSON string value you emit in any .logs/*.json file or JSON response. The downstream parsers (jq, python3 -c "json.loads(...)", prepare-phase3-data.sh, validate-enriched-trends.sh) interpret ASCII U+0022 (") as the JSON string delimiter. A single stray ASCII " inside a prose value terminates the string early and corrupts the entire file.

  • Quote pairing in prose: When you need typographic quotes inside a JSON string in DE mode, pair them correctly. The German opening quote U+201E („, low-9 quotation mark) MUST be closed with U+201D (”, right double quotation mark). Never close it with ASCII U+0022 ("). The same discipline applies to FR/IT/ES (guillemets « » U+00AB/U+00BB) and any future locale: typography pairs with typography, never with ASCII.
  • ASCII " is reserved: Inside a JSON string value, the bare ASCII double-quote U+0022 is reserved for the JSON delimiter itself. If ASCII " must appear in prose (e.g. quoting an English term inside a DE sentence), escape it as \". Better: use the locale-appropriate typographic pair instead.
  • Self-check before Write: Construct the payload as a Python dict and serialize with json.dumps(payload, ensure_ascii=False, indent=2) rather than hand-assembling JSON with string concatenation. json.dumps will refuse to produce invalid output, so a stray ASCII " inside a prose value is impossible by construction. If you must template JSON manually, validate the result with json.loads(rendered) before calling Write — and on failure, repair the offending ASCII closer (") with U+201D (”) for that span and re-validate. This is a hard gate, not advisory: one mismatched pair blocks the next phase for the whole project.

Read the full file on GitHub · 352 lines

Changes

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.

  1. 1mo ago Changed e3cff3a329c4
  2. 1mo ago Changed 9e596b5a1d08
  3. 1mo ago Changed 1b1f31a7dc57
  4. 1mo ago First seen · 352 lines · 55 tokens per session scan A 88f2f6a87f66

Subscribe to this mod's changes

trend-report-investment-theme-writer is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 5,586 once invoked, about $0.0002 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.

Related

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

anthropics/claude-cookbooks · 52 tokens

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.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens