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.
git clone --depth 1 https://github.com/cloudrift-ai/emmyWrote 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/cloudrift-ai/emmy/architecture)<a href="https://agentmods.dev/commands/cloudrift-ai/emmy/architecture"><img src="https://agentmods.dev/badge/commands/cloudrift-ai/emmy/architecture/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/cloudrift-ai/emmy/architecture"><img src="https://agentmods.dev/badge/commands/cloudrift-ai/emmy/architecture.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 | $0.00000 | $0.21035 |
| Opus 5.5 | $0.00000 | $0.08414 |
| Sonnet 5.5 | $0.00000 | $0.04207 |
| Haiku 4.5 | $0.00000 | $0.02104 |
Grade C, and why
ARCHITECTURE scanned grade C with 2 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 today.
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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
emmy deploy ssh --recipe <path> --ssh user@host[:port] [--ssh-key ~/.ssh/id_ed25519] [--dry-run] [--teardown] Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -x URL https://registry-1.docker.io/v2/` gets no HTTP status back through the proxy. The same six variables, in How it starts
The opening of the file, as written. The whole thing — 1,082 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commands Architecture
Layered Design
commands/bench ──► benchmark (config, tasks, execution)
commands/bench ──► deploy (DeployParams, deploy/teardown)
commands/bench ──► provisioning (cloud VM lifecycle)
commands/deploy ─► deploy (DeployParams, deploy/teardown)
commands/deploy ─► provisioning (remote setup, cloud VMs)
commands/vm ────► provisioning (create/delete instances)
commands/recipe ─► recipe (catalog queries and onboarding shell creation)
recipe/query ───► provisioning (read-only CloudRift availability and team access)
commands/publish ─► publish (image naming, metadata, collision and digest gates)
Dependency rule: commands/ is the CLI-only layer. All reusable business logic lives in top-level library packages:
emmy/recipe/— recipe loading, dataclass types (Recipe,LLMConfig, etc.), engine flag mapping, catalog queries, and onboarding shell creationemmy/deploy/— compose generation, deploy orchestrationemmy/provisioning/— VM types, SSH polling, shell helpers, cloud providersemmy/publish.py— the canonical serving-image name parser, model slug, Docker metadata gates, and publication runneremmy/serving/release.py— shell-free pinned serving-config parsing and the exact realization matrix shared by trace and evalemmy/logging_setup.py— CLI logging setup (setup_cli_logging()), which suppresses routine HTTP request INFO records so versioned JSON remains parseable, plusensure_plugin_logging()— makes emmy INFO logs visible when nothing configured logging (a bare vLLM entrypoint; called byemmy.serving.register())emmy/config.py— the single owner ofos.environfor allEMMY_*config vars. Typed getters (tune_db_path,nvcc_flags,debug_enabled,dump_dir,tune_patience,bench_backends_raw,cubin_cache_dir, …) read the env live;set_nvcc_flags(cli_value, default)holds the--nvcc-flags> env > command-default precedence that used to live in this CLI layer, so every callsite (CLI, programmatic, tests) shares it. The thincompile.apply_nvcc_flags/compile.resolve_tune_dbwrappers just adapt argparse to it. (Provider/secret vars stay withredact.py; the dynamicEMMY_<KNOB>namespace stays withcompiler/pipeline/knob.py, which borrowsconfig.knob_var/config.knob_raw.)emmy/redact.py—redact_secrets(),SecretRedactingFilter,install_redaction()(attach the filter to a handler — must be a handler, not a logger, so child-logger records that propagate up are still redacted),register_secret()(call after resolving any secret from a CLI flag —--hf-token,--api-key— or env var so its value is added to the redaction set)emmy/benchmark/— config, logging, workload, tasks, execution, and YAML experiment records
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.
- today Changed · +16 lines a12cabcd776d
- yesterday Changed · +7 lines 68b8d9c35afa
- 3d ago Changed · +1 lines ab30f0f484b6
- 5d ago Changed · +8 lines 74e21a095de9
- 6d ago Changed · +11 lines b1179aa4d752
- 7d ago Changed · -4 lines 3545f350eae2
- 8d ago Changed · +6 lines 741e42801ea7
- 9d ago Changed · +21 lines 8ac2fd23ac37
- 10d ago Changed · +10 lines fb8186e047ca
- 11d ago First seen · 1,006 lines · 0 tokens per session scan C a96e388725ca
ARCHITECTURE is a command published in the GitHub repository cloudrift-ai/emmy (116 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 21,035 tokens. A static security scan graded it C with 2 findings (reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
command-template.claude
Command "command-template.claude" from Enovatr-Labs/SpecRoute, covering what this command does, implementation, inline shell commands the slash command runs, output and when to use.
status
Report the current state of the SpecRoute skeleton - which top-level dirs exist, which artifacts have been drafted, what's outstanding.
JOKER
Joker parameter is used instead of executing the task result if jokers value meets the expectations requirements.
ACTION
Actions influences from the pipeline or task into external world. Like turning on a light, sending an email, etc.
FORMFACTOR
Specifies the application type and interface requirements that this promptbook should conform to.
/opsx-explore
Enter explore mode - think through ideas, investigate problems, clarify requirements.