lock-e2e

A command that turns a verified reusable action into a fixed end-to-end test. End-to-end means checking a complete user journey through the running app.

In plain words
What is it for?
Use it to freeze a parameter-free action as a strict regression test, especially for formal pull-request checks such as login verification.
Why use it?
It catches flows that only pass when automatic repair is allowed and creates a test file that can be included in a test suite.

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/lykhoyda/rn-dev-agent/lock-e2e
Clone the repo
git clone --depth 1 https://github.com/Lykhoyda/rn-dev-agent
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 296 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 $0.00060 $0.00296
Opus 5 $0.00030 $0.00148
Sonnet 5 $0.00012 $0.00059
Haiku 4.5 $0.00006 $0.00030

Measured 2d ago against content hash e1b6ccd3c433, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lock-e2e 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.

packages/claude-plugin/commands/lock-e2e.md · 16 lines

What it actually says

Lock the action into a locked e2e test: $ARGUMENTS

Steps:

  1. Call cdp_lock_e2e_test with actionId = the first positional arg (add relock: true if --relock is present).
  2. If it returns STRICT_RUN_FAILED, tell the user the action must pass a strict (no-repair) run first — offer to run cdp_run_action to repair it, then retry the lock.
  3. If it returns PARAMS_UNSUPPORTED, explain that v1 supports param-free tests only.
  4. On success, report the frozen file path and that it will now be included in cdp_run_e2e_suite.
  5. For login, this locked test is the formal PR proof on the exact candidate. cdp_login_prologue is only a navigation helper and must not be treated as that proof.
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 · 16 lines · 60 tokens per session scan A e1b6ccd3c433

Subscribe to this mod's changes

lock-e2e is a command published in the GitHub repository Lykhoyda/rn-dev-agent (11 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 296 once invoked, about $0.0003 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.