e2e-cli-test

An end-to-end test procedure for the HeyGen command-line tool, which controls HeyGen’s video-generation API. It builds the tool and tests authentication, reads, errors, and the full video creation workflow against the live service.

In plain words
What is it for?
Pre-release testing of login, account lookup, video and template listing, schema and error handling, and creating, checking, downloading, and deleting a video.
Why use it?
It checks whether a new build works in realistic conditions before release. The procedure also reports later failures instead of hiding them after the first problem.

Skill for Claude CodeCodex

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 skills/heygen-com/heygen-cli/e2e-cli-test
Any agent
npx skills add heygen-com/heygen-cli --skill e2e-cli-test
Clone the repo
git clone --depth 1 https://github.com/heygen-com/heygen-cli

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,290 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 $0.00071 $0.02290
Opus 5 $0.00036 $0.01145
Sonnet 5 $0.00014 $0.00458
Haiku 4.5 $0.00007 $0.00229

Measured 2d ago against content hash ec8445d187bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

e2e-cli-test 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.

.claude/skills/e2e-cli-test/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

E2E CLI Test

Pre-release validation that exercises ./bin/heygen against the live HeyGen API.

Prerequisites

  • HEYGEN_API_KEY must be set in the environment
  • Working directory must be the heygen-cli repo root

Workflow

Run each phase in order. Report results as you go. If a phase fails, continue to the next phase (do not abort early) so the final report covers everything. Always use ./bin/heygen (the freshly built binary), never a globally installed heygen.

Step 1: Build

make build

If this fails, stop and report the build error. Nothing else can run.

Step 2: Phase 1 -- Auth and account

./bin/heygen auth status
./bin/heygen user me get
  • Assert auth status exits 0
  • Assert user me get exits 0, stdout is valid JSON, and jq -e '.data.username' succeeds
  • If either command fails, stop and report the auth error. Every subsequent phase requires a valid key.

Step 3: Phase 2 -- Read-only list commands

Run each command below. Assert exit 0 and valid JSON stdout for every one. Save the JSON output from each -- Phase 3 will extract IDs from these results.

./bin/heygen video list --limit 1
./bin/heygen template list --limit 1
./bin/heygen ai-clipping list --limit 1
./bin/heygen avatar list --limit 1
./bin/heygen avatar looks list --limit 1
./bin/heygen voice list --limit 1
./bin/heygen audio sounds list --query "calm ambient piano" --limit 1
./bin/heygen video-translate list --limit 1
./bin/heygen video-translate languages list
./bin/heygen video-agent list --limit 1
./bin/heygen video-agent styles list --limit 1
./bin/heygen lipsync list --limit 1
./bin/heygen webhook endpoints list
./bin/heygen webhook event-types list
./bin/heygen webhook events list
./bin/heygen brand kits list --limit 1
./bin/heygen brand glossaries list --limit 1

asset list requires --username (the workspace member whose assets to list, the owner value on asset items) while the endpoint is in beta. Use the .data.username captured in Phase 1 (user me get): ./bin/heygen asset list --username <phase-1-username> --limit 1.

Read the full file on GitHub · 217 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. 2d ago First seen · 217 lines · 71 tokens per session scan A ec8445d187bf

Subscribe to this mod's changes

e2e-cli-test is a skill published in the GitHub repository heygen-com/heygen-cli (113 stars, last pushed 3d ago), licensed Apache-2.0. It adds 71 tokens to every session and 2,290 once invoked, about $0.0004 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.