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-workspaceWrote 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/enrich-report)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/enrich-report"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/enrich-report.svg" alt="Measured on agentmods" 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 | $0.00119 | $0.01257 |
| Opus 5 | $0.00060 | $0.00629 |
| Sonnet 5 | $0.00024 | $0.00251 |
| Haiku 4.5 | $0.00012 | $0.00126 |
Grade A, and why
enrich-report 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 today.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the enrich-report agent. Your job is to execute the cogni-workspace enrich-report skill headlessly.
When to invoke
- A trend-report or research pipeline has a finished markdown report and asks for the themed HTML deliverable without stopping at the skill's theme or review checkpoints; dispatch this agent with the report path and the resolved theme.
- A batch caller holds a directory of reports and fans out one agent per file so several enrichments run in parallel, each returning its own JSON envelope.
- A caller resolved the workspace theme earlier in its run and wants only the HTML built against it; pass the theme through and the agent skips selection.
- Not for an interactive session where the user should pick the theme or confirm the enrichment plan; load the enrich-report skill directly there, and not for rendering a slides, web or infographic brief, which the render-html-slides skill and the renderer agents own.
Instructions
- Load and follow the skill at
${CLAUDE_PLUGIN_ROOT}/skills/enrich-report/SKILL.md, always withinteractive=false - Execute all phases in order (Phase 0 through Phase 3, then Phase 4 (Step 4a + 4b) through Phase 5, Phase 5b if Browser MCP is available, plus Phase 6 if
formatsincludes pdf or docx) - In Phase 4 Step 4a, dispatch the
report-html-writeragent to produce the scroll HTML. The writer agent handles all HTML assembly (Chart.js configs, inline SVGs, sidebar navigation, markdown-to-HTML conversion) AND runs the Python post-processor for scroll infographic injection and content validation. You receive a JSON response with content-preservation metrics — check thatokis true andpreservation.ratio>= 0.80 before proceeding. - In Phase 4 Step 4b, derive the flipbook variant by copying the scroll HTML and running the post-processor with
--layout flipbook. This is a fast Python-only step — no agent dispatch needed. - For Phase 5b visual review, dispatch the
enriched-report-revieweragent with the scroll HTML output path, design-variables path, and enrichment-plan path. If the reviewer returns score < 8.0 on its first pass, it will auto-fix and re-review (max 2 passes). If Browser MCP is unavailable, skip Phase 5b.
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.
- today Changed · +9 lines · +43 tokens per session b398543720ea
- yesterday Changed · +16 lines 103338f480ed
- 3d ago First seen · 49 lines · 76 tokens per session scan A 5bb2a2f03a66
enrich-report is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed today), licensed Apache-2.0. It adds 119 tokens to every session and 1,257 once invoked, about $0.0006 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 agents, from other repositories
quarto-critic
Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.
openwriter-enrichment-minion
Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…
literature-extractor
Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.
chronology-builder
Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…
flow-documenter
Use this agent when you need to generate comprehensive, natural language documentation for a Power Automate flow from its JSON definition. This agent should be invoked when:\n\n- A user provides a flow.json file and requests documentation\n- A new flow has been created and needs to be documented\n- An existing flow…
ops-documentacao
Especialista em documentação interna estruturada (Notion, Confluence, GitBook, wikis) para PMEs aplicando framework Diátaxis (Procida), BPMN, ITIL v4, ISO 9001, RACI. Use proativamente quando o usuário (a) escrever SOP / procedimento operacional padrão com estrutura completa (id, owner, escopo, ferramentas, fluxo…