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.
curl -O https://raw.githubusercontent.com/Contoso-State/red-team-agent-orchestration/main/.claude/commands/assess.mdgit clone --depth 1 https://github.com/Contoso-State/red-team-agent-orchestrationWrote 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/commands/contoso-state/red-team-agent-orchestration/assess)<a href="https://agentmods.dev/commands/contoso-state/red-team-agent-orchestration/assess"><img src="https://agentmods.dev/badge/commands/contoso-state/red-team-agent-orchestration/assess/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/commands/contoso-state/red-team-agent-orchestration/assess"><img src="https://agentmods.dev/badge/commands/contoso-state/red-team-agent-orchestration/assess.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 | $0.00017 | $0.01594 |
| Opus 5.5 | $0.00007 | $0.00638 |
| Sonnet 5.5 | $0.00003 | $0.00319 |
| Haiku 4.5 | $0.00002 | $0.00159 |
Grade A, and why
assess 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/assess — Full Security Assessment
You are acting as the Orchestrator Agent (agents/orchestrator/system-prompt.md). Complete the
canonical assessment graph in graph/redteam.graph.json, including scope validation, methodology
memory, preflight, specialist assessment, bounded evaluation, judging, correlation, reporting, and
debrief. Graph execution and evidence-gated methodology learning are enabled by default; respect
and report an explicit REDTEAM_SELF_IMPROVE=off override. You remain dispatch-only: shell and
Azure operations belong to the authorized runtime host or delegated specialists.
Preconditions
engagement.yamlexists and is valid.scope.subscriptionscontains exactly one target subscription.engagements/<session>/inventory/resources.jsonlexists (run/reconfirst if not).engagements/<session>/engagement.dbexists with the inventory ingested (run/reconfirst if not).
Steps
- Stand up the Agent Observatory. Have the authorized runtime host or a delegated specialist
start
node tools/dashboard/server.mjs --session engagements/<session>and emit redacted lifecycle, actual handoff, memory, and evaluation metadata throughtools/dashboard/events.mjs. The standalonetools/graph/run-graph.mjsuses simulated dispatch. The separatetools/graph/run-live.mjsuses the Claude live adapter and requires explicit scope and fresh preflight; other runtimes use native agent dispatch and must emit their own events. Report dashboard failures without blocking assessment. - Validate scope and load methodology memory. Revalidate the engagement and identity/permission preflight requirements before assessment. After scope validation, retrieve evidence-verified, bounded prior-run context for the same environment and agent. Keep source run references; candidates remain inert and reusable knowledge requires at least two distinct corroborating runs. Historical observations do not prove current findings or justify automatic suppression.
- Confirm inventory is present and current, and preflight permissions are validated. If missing, dispatch reconnaissance first. Domain agents should read inventory and cached config facts from the datastore (
node tools/datastore/query.mjs resources|facts|neighbors --db engagements/<session>/engagement.db …) before calling Azure — only hitaz/ARG on a cache miss or a stale fact (query.mjs fresh … --ttl <seconds>). - Dispatch domain agents based on resource types in the inventory. Pass each its verified methodology context. Each agent runs its checks from
checks/<domain>/and writes findings toengagements/<session>/findings/raw/<agent>.jsonl:
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.
- 1mo ago Changed · +17 lines e0c1602cd8d5
- 1mo ago Changed · +15 lines eb5803b0e7e8
- 1mo ago First seen · 50 lines · 17 tokens per session scan A 795f4047c959
assess is a command published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 1,594 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
cost-optimize
Reduce cloud costs across AWS, Azure, and GCP through rightsizing, reserved and spot capacity, storage tuning, and cost monitoring.
deploy
Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.
env
Manage Vercel environment variables. Commands include list, pull, add, remove, and diff. Use to sync environment variables between Vercel and your local development environment.
firebase-publish
Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.
scan
Scan AWS account for cost optimization.
finops-status
Orientation — say where an opportunity or assignment sits in the five-step FinOps lifecycle and what unlocks next. Useful when a record has no active stage: an opportunity while its assignments do the work, an assignment whose plan has not been approved yet, or a rejected or archived assignment. Read-only; mutates…