A report-generation command for turning Azure security findings into an executive summary and a technical assessment report. It refreshes, checks, and exports the collected results.

Use it after an assessment to normalize findings, validate the report data, and export findings, coverage, resource inventory, and summary files.

It removes the manual work of combining duplicate findings and producing consistent report files. It also prevents old findings from being carried into a new report.

How Contoso-State/red-team-agent-orchestration configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Contoso-State/red-team-agent-orchestration. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Contoso-State/red-team-agent-orchestration/main/.claude/commands/report.md

Clone the repo

git clone --depth 1 https://github.com/Contoso-State/red-team-agent-orchestration

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/contoso-state/red-team-agent-orchestration/report/github.svg)](https://agentmods.dev/commands/contoso-state/red-team-agent-orchestration/report)

Your own site

<a href="https://agentmods.dev/commands/contoso-state/red-team-agent-orchestration/report"><img src="https://agentmods.dev/badge/commands/contoso-state/red-team-agent-orchestration/report/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/contoso-state/red-team-agent-orchestration/report"><img src="https://agentmods.dev/badge/commands/contoso-state/red-team-agent-orchestration/report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,139 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.

Model	Per session	Once invoked
Fable 5.1	$0.00014	$0.01139
Opus 5	$0.00007	$0.00570
Sonnet 5	$0.00003	$0.00228
Haiku 4.5	$0.00001	$0.00114

Measured 9d ago against content hash a86f9789b01c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 9d 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.

.claude/commands/report.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/report — Generate Assessment Report

You are acting as the Reporting Agent (agents/reporting/system-prompt.md). Turn raw findings into the final deliverables.

Preconditions

engagements/<session>/findings/raw/*.jsonl is populated (run /assess and ideally /attack-paths first).
engagements/<session>/engagement.db exists with findings ingested (the canonical, deduplicated source).

Steps

Refresh findings from current raw inputs, then export canonical artifacts. Always run findings ingest in replace mode first so stale DB rows from prior passes cannot leak into this report:
- node tools/datastore/ingest.mjs --db engagements/<session>/engagement.db --session engagements/<session> --findings engagements/<session>/findings/raw --replace-findings
- node tools/datastore/export.mjs --db engagements/<session>/engagement.db --session engagements/<session> --what all This writes findings/normalized/findings.json, reports/findings.json, coverage.json, inventory/resources.jsonl, and inventory/summary.json.
Validate the exported engagements/<session>/reports/findings.json against schemas/finding.schema.json (node tools/validate-findings.mjs); fix or drop malformed entries at the source and re-export.
Confirm deduplication. The DB already deduplicates by dedupe_key (falling back to id) and unions affected_resources[]; spot-check that the same misconfiguration across resources collapsed into one aggregated finding.
Reconcile severity using knowledge/severity-model.md. You set the final severity consistently.
Promote attack paths from the Authorization & Attack Path Agent to the top.
Map controls (CIS Azure, MITRE) from controls/.
Surface coverage limitations from engagements/<session>/inventory/coverage-limitations.json.
Promote the run into history and surface deltas. node tools/datastore/promote.mjs --db engagements/<session>/engagement.db --history engagements/_history/<engagement.id>.db --out engagements/<session>/reports/delta.json. Lead the executive summary's "What changed" with the resulting new / persisting / resolved / regressed counts (the first run has no prior, so everything is new).
Render:
- engagements/<session>/reports/executive-summary.md (from reports/templates/executive-summary.md)
- engagements/<session>/reports/technical-report.md (from reports/templates/technical-report.md)
- engagements/<session>/reports/assessment-deck.md (from reports/templates/assessment-deck.md) — the PowerPoint-convertible slide deck. Follow the slide rules in that template (## titles, --- separators, one idea per slide). See /deck for the standalone flow and conversion commands.
- engagements/<session>/reports/findings.json (normalized canonical set)
- engagements/<session>/reports/report.html — the interactive HTML report, generated from findings.json (a print-first consulting deliverable: cover, contents, executive summary, attack paths, findings, prioritized recommendations, asset/scope inventory, a consolidated pan/zoom attack graph, and appendices):

Read the full file on GitHub · 65 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.

9d ago First seen · 65 lines · 14 tokens per session scan A a86f9789b01c

Subscribe to this mod's changes

report is a command published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 5d ago), licensed MIT. It adds 14 tokens to every session and 1,139 once invoked, about $0.0001 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 2026-08-31.

Documents Security

brand-generate

Generate an on-brand document from a saved Brand Profile.

ferdinandobons/brand-docs · 0 tokens

cti-report

Render case deliverables — relationship graph (PNG/SVG/Mermaid) and a polished PDF/DOCX assessment. Usage: /cti-report [--graph|--pdf].

7onez/cti-expert · 45 tokens

prose-review-docs

Reviews markdown documentation files or directories against the active prose style rules — the plugin's vendor-neutral baseline plus your organization's overlay when one is configured. Accepts a file path or directory (recursive). Runs prose-style-checker and optionally Vale. Supports --fix to auto-apply safe…

ihudak/ihudak-claude-plugins · 67 tokens

red-team-agent-orchestration: Command for Claude Code