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-portfolioWrote 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/portfolio-verify)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/portfolio-verify"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/portfolio-verify/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/portfolio-verify"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/portfolio-verify.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 | $0.00072 | $0.03140 |
| Opus 5 | $0.00036 | $0.01570 |
| Sonnet 5 | $0.00014 | $0.00628 |
| Haiku 4.5 | $0.00007 | $0.00314 |
Grade A, and why
portfolio-verify 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 6d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portfolio Claim Verification
Verify web-sourced claims submitted by portfolio research agents against their cited sources. This is the quality gate between enrichment and communicate.
Core Concept
Plugin root resolution. Bash invocations below resolve the plugin root inline as ${CLAUDE_PLUGIN_ROOT:-$(ls -td "$HOME"/.claude/plugins/cache/insight-wave/cogni-portfolio/*/ | head -1)} — the first call works whether or not the harness injects $CLAUDE_PLUGIN_ROOT. Keep the inline form in every call; do not strip it.
Research agents (market-researcher, competitor-researcher, proposition-generator) pull data from the web — market sizes, growth rates, competitor claims, industry benchmarks. Each web-sourced fact is logged as a claim in cogni-claims/claims.json with its source URL. But web data goes stale, gets misread, or comes from unreliable sources.
Verification catches these problems before they propagate into deliverables. The claim-verifier agent revisits each source URL, compares what was claimed against what the source actually says, and flags deviations by severity. A "TAM of $4.2B" that the source actually quotes as $2.4B is a critical deviation — it would undermine every proposal built on that number.
This matters because downstream outputs (synthesis, exports, proposals) inherit whatever the portfolio contains. Catching a wrong number here is cheap; catching it in a client presentation is expensive. The verification gate gives the user a clear picture of data quality and the chance to correct problems while they're easy to fix.
Prerequisites
This skill depends on the cogni-workspace:claims skill, which performs the actual source-checking. If that skill is not available, tell the user cogni-workspace is not installed and point them at its installation instructions.
If no cogni-claims/ directory exists in the project, no claims have been submitted yet. Research agents submit claims automatically when web search is used during market research, competitor research, and proposition generation. Suggest running those skills with web research enabled first.
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.
- 6d ago First seen · 254 lines · 72 tokens per session scan A a7a2e3d1e98d
portfolio-verify is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 3,140 once invoked, about $0.0004 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…