run

A command that sends a requirement to the Saddle service and runs its default agent workflow, optionally using a named mode. Saddle is a service for running staged development pipelines.

In plain words
What is it for?
Use it to run a Saddle pipeline from a requirement such as adding a login form or refactoring an API.
Why use it?
It provides one entry point for processing a requirement through the configured workflow and reports any failed stages.

Command

Install

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.

agentmods
npx agentmods add commands/deepelementlab/saddle/run
Clone the repo
git clone --depth 1 https://github.com/deepelementlab/saddle
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 337 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.00337
Opus 5 $0.00008 $0.00169
Sonnet 5 $0.00003 $0.00067
Haiku 4.5 $0.00002 $0.00034

Measured 2d ago against content hash b06e20a869d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run 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.

plugins/claude-code-plugin/commands/run.md · 33 lines

What it actually says

Runs saddle run through POST /api/v1/pipeline/run on SADDLE_BASE_URL (requires saddle serve).

Invoke

node "${CLAUDE_PLUGIN_ROOT}/commands/scripts/run-pipeline.js" "$ARGUMENTS"

Ways to pass input

  1. One string: the requirement text, with optional suffix --mode fast (or another mode name).
  2. Two tokens: "requirement text" modeName (mode must be a single identifier-like token).

Examples for $ARGUMENTS:

  • Add login form --mode fast
  • Refactor the API fast (two arguments)

After the command: summarize whether the pipeline succeeded (ok / result.stages), highlight any stage failures, and suggest next steps. If the user sees HTTP errors, tell them to run python -m saddle serve from the project root and retry.

Fallback: the script may run python -m saddle run locally if the API is unreachable; set SADDLE_PYTHON to the correct interpreter if needed.

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.

  1. 2d ago First seen · 33 lines · 15 tokens per session scan A b06e20a869d4

Subscribe to this mod's changes

run is a command published in the GitHub repository deepelementlab/saddle (5 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 337 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.