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/valkor-ai/loom/loom-deploygit clone --depth 1 https://github.com/valkor-ai/loomWrote 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/valkor-ai/loom/loom-deploy)<a href="https://agentmods.dev/commands/valkor-ai/loom/loom-deploy"><img src="https://agentmods.dev/badge/commands/valkor-ai/loom/loom-deploy.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 | $0.00007 | $0.00354 |
| Opus 5 | $0.00003 | $0.00177 |
| Sonnet 5 | $0.00001 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
loom-deploy 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 4d 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
You are executing /loom-deploy $ARGUMENTS now.
Call the matching Loom MCP deploy tool for the current project directory:
- empty ->
loom.deployRun prepare->loom.deployPrepareup->loom.deployUpstatus->loom.deployStatusinspect->loom.deployInspectvalidate->loom.deployValidatelogs->loom.deployLogsbootstrap->loom.deployBootstrapdown->loom.deployDownrepair->loom.deployRepair
Follow the returned MCP action result and do not create deployment assets or repair scopes outside that result. For user_gate with preResponseContract, execute the contract before any visible response: call loom.inspectRequest, then call loom.readFieldGroup for only required requestReadPlan.groups. During active_operation, call only the observation tools named by the result, obey observationPolicy, obey forbiddenActions, and do not report completion while finalResponsePolicy forbids it. During asset repair, edit only returned generated deployment assets or modelRepairRef; never edit generated source-model/topology/facts snapshots directly. Then call the returned retryTool; do not use loom.deployRun as a repair retry.
If the MCP result includes deployReferenceProfile.referenceLoadPlan, load the installed loom-deploy skill and follow its Reference Loading section. This command must not maintain a separate deploy reference path map.
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.
- 4d ago First seen · 24 lines · 7 tokens per session scan A 9c2ec19345f5
loom-deploy is a command published in the GitHub repository valkor-ai/loom (949 stars, last pushed 18d ago), licensed Apache-2.0. It adds 7 tokens to every session and 354 once invoked, about $0.0000 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
deploy
Build, test, deploy with staged rollout.
deploy
Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.
cf-scaffold-project
Scaffold a Cloudflare project — Worker, Pages, or Worker+D1+R2 starter — with Wrangler config, Terraform skeleton, and GitHub Actions deploy using scoped API tokens.
overview
Unified cost dashboard combining state, plan, actual costs, projected costs, drift, and recommendations.
scan
Scan AWS account for cost optimization.
finops-feedback
Step 5 (Feedback Loop & Celebration) — measure realized against projected savings, compute a labelled Cloud Entropy proxy, close the opportunity, and emit at least one new idea or policy update so the loop actually closes. Applies the double-loop gate. Mutates on the closure path.