agentmods.dev

local-run

local-run is a skill for Claude Code, Codex from me-cedric/agent-compass. It costs 33 tokens per session (1,040 once invoked), scanned A, original, MIT.

A local development runner for starting project applications with process-compose and Docker Compose. Docker Compose starts related services from a configuration file.

In plain words
What is it for?
Use it to run a local application stack, create or adapt a process-compose configuration, and handle local web or mobile app setup.
Why use it?
It provides a controlled way to draft, start, restart, or debug local services while checking prerequisites such as Docker, ports, VPN access, and environment values.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 3repo 4d ago A scan 33 tokens original MIT

Good fit Use it to run a local application stack, create or adapt a process-compose configuration, and handle local web or mobile app setup.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/me-cedric/agent-compass/local-run
View source ↗ me-cedric/agent-compass
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.

Any agent
npx skills add me-cedric/agent-compass --skill local-run
Clone the repo
git clone --depth 1 https://github.com/me-cedric/agent-compass

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for local-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/me-cedric/agent-compass/local-run/github.svg)](https://agentmods.dev/skills/me-cedric/agent-compass/local-run)
Your own site
<a href="https://agentmods.dev/skills/me-cedric/agent-compass/local-run"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/local-run/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.

agentmods 80×15 button for local-run

Your own site · 80×15
<a href="https://agentmods.dev/skills/me-cedric/agent-compass/local-run"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/local-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,040 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00033 $0.01040
Opus 5.5 $0.00013 $0.00416
Sonnet 5.5 $0.00007 $0.00208
Haiku 4.5 $0.00003 $0.00104

Measured 10d ago against content hash ce2f7bfe3c53, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

local-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 10d 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.

packs/local-run/skills/local-run/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

local-run

Run the local stack with ac dev. One file, process-compose.yaml, lists every process. Never start process-compose directly. ac dev sets the socket path and the timeouts.

1. Ask before you write

Ask for each input that the repository does not show. Ask one question at a time. Do not guess.

  • Secrets: use the env skill and ac env import to get the values. Never ask the user to paste a secret in chat.
  • VPN: does an app or a registry need it? Is it on?
  • Corporate certificates: when Node fails with a certificate error, set NODE_EXTRA_CA_CERTS to the CA file. Or set NODE_OPTIONS=--use-system-ca.
  • Docker: is the daemon running? Check with docker info. Dockerfiles and a compose file to adapt are in docs/agent-compass/packs/local-run/extras/. Sync does not install them.
  • Mobile: which target? iOS needs Xcode and a simulator. Android needs the SDK and an emulator.
  • Apps: which apps must run now? Which ports are already in use?

2. Start from a draft

ac dev up --dry

When process-compose.yaml is missing, this prints a draft on stdout. It writes nothing. The draft has one infra process for the first compose file. It has one process for each app with a dev script. When the file exists, the same command validates it.

Read the warnings. A missing port means the process has no readiness probe. Two apps on one port is a clash. Save the draft as process-compose.yaml. Then edit it.

3. Write the file

For each app process:

  • Add a readiness_probe on the app port. The draft uses nc -z 127.0.0.1 <port>.
  • Add a log_location of .agents/dev/logs/<name>.log.
  • Set working_dir relative to the repository root.
  • Make the app wait for infra with condition: process_completed_successfully.
  • Use process_healthy when an app waits for another app with a probe.

Put infrastructure services in docker compose profiles:

services:
  db:
    image: postgres:17
    profiles: [infra]

Start them from the infra process:

Read the full file on GitHub · 106 lines

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. 10d ago First seen · 106 lines · 33 tokens per session scan A ce2f7bfe3c53

Subscribe to this mod's changes

local-run is a skill published in the GitHub repository me-cedric/agent-compass (3 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 1,040 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 2026-10-18.

ContainersDevOps and cloudagent-skillsagentic-aiaiai-agentsautomationclaude
Related

Other skills, from other repositories

agent-sandbox

Agent skill for sandbox - invoke with $agent-sandbox.

ruvnet/ruflo · 15 tokens

github-actions-templates

Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.

wshobson/agents · 44 tokens

cdf-orchestration-setup

Use when the user asks to deploy, install, reinstall, redeploy, upgrade, or connect to the CDF Orchestration Airflow controller. Owns the end-to-end deploy sequence and runs the cdf-orchestration-preflight audit first. Covers make setup, controller image builds, Helm installation, controller connection…

NVIDIA/skills · 105 tokens

aiq-deploy

Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.

NVIDIA/skills · 27 tokens

dynamo-recipe-runner

Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.

NVIDIA/skills · 49 tokens

kermt-monitor

Check progress for a detached KERMT run (pretrain, finetune, or any kermtrundetached invocation). Reads run.json, queries docker for container state, tails the pretrain/finetune log, and parses progress lines (epoch, step, val loss).

NVIDIA/skills · 64 tokens