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.
npx agentmods add commands/timothywarner-org/claude-code/deploy-genaigit clone --depth 1 https://github.com/timothywarner-org/claude-codeWhat 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 | $0.00022 | $0.00373 |
| Opus 5 | $0.00011 | $0.00187 |
| Sonnet 5 | $0.00004 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
deploy-genai 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 2d 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.
What it actually says
/deploy-genai
Ship the current Python GenAI app to Azure the keyless way. Target environment: $1 (default to staging if empty).
Follow this order and stop at the first gate that fails.
-
Run the eval gate. Invoke the
genai-prompt-evalskill against the app's eval cases. If any dimension is below threshold, stop and report the failing dimension. A prompt regression does not ship. See [[testing]]. -
Confirm keyless auth. Verify the client uses
DefaultAzureCredential+get_bearer_token_provider, with noapi_key=argument and no key read from the environment. If a key path is present, stop and fix it first. See [[secrets-security]]. -
Preflight env. Run the
azure-ai-deployskill'spreflight.pyto confirmAZURE_OPENAI_ENDPOINTand the deployment name are set. Non-zero exit stops the deploy. -
Provision and deploy with azd. Run
azd provisionthenazd deploy(orazd upfor a fresh environment) against $1. Do not hand-writeazdeploy commands. See [[azure-deployment]]. -
Verify. Hit the deployed endpoint with one smoke request and confirm a grounded response, then report the deployment URL and the eval scores that gated it.
Use the azure MCP tools and Microsoft Learn MCP to confirm any current portal path or SDK shape before asserting it.
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.
- 2d ago First seen · 23 lines · 22 tokens per session scan A a3697f638191
deploy-genai is a command published in the GitHub repository timothywarner-org/claude-code (223 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 373 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.