agent-swarm: Skill for Claude Code

.claude/internal-skills/swarm-local-e2e/SKILL.md

swarm-local-e2e is a skill for Claude Code from desplega-ai/agent-swarm. It costs 36 tokens per session (2,717 once invoked), scanned B, original, MIT.

A guide for testing an agent swarm from start to finish on a local computer. End-to-end testing checks a complete workflow, including the API, containers, tasks, logs, and dashboard.

In plain words
What is it for?
Use it to verify task handling, session logs, Docker startup, API endpoints, or the user interface after changes.
Why use it?
It helps find failures that only appear when the whole system runs together, rather than when individual parts are tested alone.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is desplega-ai/agent-swarm's own configuration. It tells Claude Code how to work on agent-swarm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-swarm configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is # Defaults to port from APP_URL in .env (check with: grep APP_URL ../.env).

Reuse

Borrowing it

Nothing to install: this file belongs to desplega-ai/agent-swarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/desplega-ai/agent-swarm/main/.claude/internal-skills/swarm-local-e2e/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/desplega-ai/agent-swarm

Made for: Claude Code.

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 swarm-local-e2e

README.md
[![agentmods](https://agentmods.dev/badge/skills/desplega-ai/agent-swarm/swarm-local-e2e/github.svg)](https://agentmods.dev/skills/desplega-ai/agent-swarm/swarm-local-e2e)
Your own site
<a href="https://agentmods.dev/skills/desplega-ai/agent-swarm/swarm-local-e2e"><img src="https://agentmods.dev/badge/skills/desplega-ai/agent-swarm/swarm-local-e2e/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 swarm-local-e2e

Your own site · 80×15
<a href="https://agentmods.dev/skills/desplega-ai/agent-swarm/swarm-local-e2e"><img src="https://agentmods.dev/badge/skills/desplega-ai/agent-swarm/swarm-local-e2e.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,717 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 13 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 37
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 192
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium MCP Rug Pull · line 77
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
  • medium MCP Rug Pull · line 97
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
  • medium Server-Side Request Forgery · line 117
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 130
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 142
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 163
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 170
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 178
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 179
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Data Exfiltration · line 130
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 142
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00036 $0.02717
Opus 5 $0.00018 $0.01358
Sonnet 5 $0.00007 $0.00543
Haiku 4.5 $0.00004 $0.00272

Measured 3d ago against content hash b9c99459263d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

swarm-local-e2e scanned grade B 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 3d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

const t = await (await fetch('http://localhost:$PORT/api/tasks', { method: 'POST', headers,

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Use `context-mode execute` (not curl directly due to hook restrictions):
.claude/internal-skills/swarm-local-e2e/SKILL.md · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Local E2E Testing Guide

Run full end-to-end tests of the agent swarm locally with a real API server and Docker containers.

When to Use This Skill

This skill should be invoked in two modes:

  1. User-requested QA: The user asks you to run E2E tests, verify a feature, or QA a specific flow. Follow the steps below targeting what they asked for.

  2. Automated change verification: After implementing changes that touch the API, runner, polling, task lifecycle, session logs, Docker entrypoint, or worker/lead behavior — use this skill proactively to verify the changes work end-to-end. Determine what's testable based on the diff:

    • Task lifecycle changes (poll, runner, store-progress): Create assigned + pool tasks, verify they complete and have correct logs
    • Session log changes: Run two sequential tasks on the same agent, verify log isolation (unique sessionIds, no cross-contamination)
    • Docker / entrypoint changes: Build image, start containers, verify boot logs and registration
    • UI changes: Start the dashboard, use agent-browser to verify rendering
    • API endpoint changes: Call the endpoint directly and verify the response

You do not need to run every step — pick the subset relevant to the changes being tested.

Prerequisites

  • OrbStack or Docker Desktop running (open -a OrbStack if needed)
  • .env with API_KEY and PORT configured
  • .env.docker-lead with lead config (AGENT_ID, CLAUDE_CODE_OAUTH_TOKEN, MCP_BASE_URL)
  • .env.docker with worker config (AGENT_ID, CLAUDE_CODE_OAUTH_TOKEN or OPENROUTER_API_KEY, MCP_BASE_URL)

Step 1: Determine Your Port

Check .env for the configured port — do not assume 3013:

grep ^PORT= .env

Use this value as $PORT throughout. In worktrees, each worktree may have a different port. Always verify and use the value from .env.

Also verify the Docker env files match:

grep MCP_BASE_URL .env.docker-lead .env.docker
# Both should point to http://host.docker.internal:$PORT

Read the full file on GitHub · 280 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. 3d ago Changed b9c99459263d
  2. 5d ago Changed · -1 lines 98c4c9d088d8
  3. 11d ago First seen · 281 lines · 36 tokens per session scan B 4fb101c9a2c7

Subscribe to this mod's changes

swarm-local-e2e is a skill published in the GitHub repository desplega-ai/agent-swarm (758 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 2,717 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

vibe-behavioral-test-capture

Builds an executable safety net of characterization tests by integrating browser flow recording, API payload snapshotting, DOM state captures, network traces, and mock fixture generation.

richfrem/agent-plugins-skills · 42 tokens

evo-smoketest

Converts temperatures between Celsius and Fahrenheit for the evolution end-to-end smoke test harness.

richfrem/agent-plugins-skills · 23 tokens

e2e-testing

Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…

QwenLM/qwen-code · 94 tokens

terminal-capture

Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.

QwenLM/qwen-code · 66 tokens

tmux-real-user-testing

A real-user test workflow for Qwen Code's terminal interface, using tmux to drive the program and capture readable screen snapshots. tmux is a tool for running and observing terminal sessions.

QwenLM/qwen-code · 98 tokens

agent-reproduce-align

Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request bodies, tool/function schemas, outputs, and iterate until the reproduced behavior is close enough.

QwenLM/qwen-code · 62 tokens