What is generate-report?

A command that builds an HTML health report from Omen project data and adds automatically written findings from several analysts.

Use it to generate, analyze, validate, and render an Omen health report, including findings about hotspots and self-admitted technical debt.

It gathers project health information, checks the results, and presents them in one report instead of requiring you to inspect each data file yourself.

generate-report — Command for coding agents by panbanda: A command that builds an HTML health report from…

Install

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.

agentmods

npx agentmods add commands/panbanda/omen/generate-report

Clone the repo

git clone --depth 1 https://github.com/panbanda/omen

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,256 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01256
Opus 5	$0.00000	$0.00628
Sonnet 5	$0.00000	$0.00251
Haiku 4.5	$0.00000	$0.00126

Measured 3d ago against content hash 3f581e9a65f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

generate-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 3d 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.

plugins/reporting/commands/generate-report.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Health Report

Generate a complete HTML health report with LLM-generated insights.

Workflow

Check for omen.toml or .omen/omen.toml. If missing, run omen-development:setup-config first.
Generate data: omen report generate -o ./omen-report-$(date +%Y-%m-%d)/
Create insights dir: mkdir -p <output-dir>/insights
Spawn analyst agents in parallel (Step 3)
Wait for all to complete, then spawn summary agent (Step 4)
Validate: omen report validate -d <output-dir>/
Render: omen report render -d <output-dir>/ -o report.html

Step 3: Spawn Analysts (In Parallel)

Use the Task tool to spawn all 13 agents simultaneously. Each agent reads its data file and writes an insight file with the schema below.

Use the hotspot-analyst agent to analyze <dir>/hotspots.json and write <dir>/insights/hotspots.json:

{"section_insight": "string", "item_annotations": [{"file": "path", "comment": "string", "verified": false, "evidence": "string"}]}

Use the satd-analyst agent to analyze <dir>/satd.json and write <dir>/insights/satd.json:

{"section_insight": "string", "item_annotations": [{"file": "path", "line": 0, "comment": "string", "verified": false, "evidence": "string"}]}

Use the ownership-analyst agent to analyze <dir>/ownership.json and write <dir>/insights/ownership.json:

{"section_insight": "string", "item_annotations": [{"file": "path", "comment": "string", "verified": false, "evidence": "string"}]}

Use the duplicates-analyst agent to analyze <dir>/duplicates.json and write <dir>/insights/duplication.json:

{"section_insight": "string"}

Use the churn-analyst agent to analyze <dir>/churn.json and write <dir>/insights/churn.json:

{"section_insight": "string"}

Use the flags-analyst agent to analyze <dir>/flags.json and write <dir>/insights/flags.json:

{"section_insight": "string", "item_annotations": [{"flag": "name", "priority": "CRITICAL|HIGH|MEDIUM|LOW", "introduced_at": "ISO8601", "comment": "string"}]}

Read the full file on GitHub · 120 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.

3d ago First seen · 120 lines · 0 tokens per session scan A 3f581e9a65f2

Subscribe to this mod's changes

generate-report is a command published in the GitHub repository panbanda/omen (18 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,256 tokens. 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 2026-08-30.

Data and AI claude-code claude-plugins cli code-analysis code-quality github-actions

generate-report

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Generate Health Report

Workflow

Step 3: Spawn Analysts (In Parallel)

What this file has done since we first saw it

Other commands, from other repositories

ask

export

reindex

review-pr

create_plan

research_codebase