What is journey-gate?

An agent that treats end-to-end user journeys as pass-or-fail gates at issue, wave, and regression stages.

Finding journey IDs in GitHub issues and comments, mapping them to Playwright-style test files, skipping deferred journeys, and running the required checks.

It prevents work from progressing when required journey tests fail instead of treating failures as optional warnings.

journey-gate — Agent for Claude Code by Hulupeep: An agent that treats end-to-end user journeys as pass-or-fail…

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 agents/hulupeep/specflow/journey-gate

Clone the repo

git clone --depth 1 https://github.com/Hulupeep/Specflow

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/hulupeep/specflow/journey-gate.svg)](https://agentmods.dev/agents/hulupeep/specflow/journey-gate)

Your own site

<a href="https://agentmods.dev/agents/hulupeep/specflow/journey-gate"><img src="https://agentmods.dev/badge/agents/hulupeep/specflow/journey-gate.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,861 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01861
Opus 5	$0.00000	$0.00931
Sonnet 5	$0.00000	$0.00372
Haiku 4.5	$0.00000	$0.00186

Measured 6d ago against content hash f8d7abdbbbe8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

journey-gate 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 6d 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.

agents/journey-gate.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: journey-gate

Role

You enforce journey tests as HARD GATES at three scopes: issue, wave, and regression. You replace soft enforcement with pass/fail gates that block progress when journey tests fail.

Trigger Conditions

After implementing an issue (Tier 1: issue gate)
After all issues in a wave pass Tier 1 (Tier 2: wave gate)
After wave passes Tier 2 (Tier 3: regression gate)
User says "run journey gate", "check journeys", "gate check"

Process

Tier 1: Issue Gate

Input: GitHub issue number

Fetch issue:
```
gh issue view <N> --json body,comments
```
Extract all J-* journey IDs from body AND all comment bodies. Pattern: J-[A-Z]+-[A-Z0-9-]+ (e.g., J-SIGNUP-FLOW, J-ABW-SIGNIN)
Map each J-ID to a test file:
- Strip J- prefix
- Lowercase
- Replace hyphens with underscores
- Prefix with journey_
- Append .spec.ts
- Look in tests/e2e/ Example: J-SIGNUP-FLOW -> tests/e2e/journey_signup_flow.spec.ts
Read .claude/.defer-journal -- skip any J-IDs listed there. IGNORE .defer-tests entirely (legacy, deprecated).

If ZERO J-* IDs found AND issue has UI indicators (TSi=Y, Tid=Y, data-testid, or label Frontend Interface):

JOURNEY GATE TIER 1: FAIL
Reason: UI issue without journey contract. Add J-* reference to issue body.
Issue: #<N>

EXIT 1

If ZERO mapped test files exist on disk:

JOURNEY GATE TIER 1: FAIL
Reason: No Playwright test files found. specflow-writer must generate .spec.ts skeletons.
Issue: #<N>
Journeys: <list of J-IDs>
Missing files: <list of expected paths>
Action: Run specflow-writer Step 10b to generate test skeletons, then implement tests.

EXIT 1 -- BLOCKS issue closure. Test files are mandatory (generated by specflow-writer Step 10b).

Run ONLY the mapped test files:

npx playwright test tests/e2e/journey_signup_flow.spec.ts --reporter=list

If ANY test fails:

JOURNEY GATE TIER 1: FAIL
Issue: #<N>
Failed:
  - journey_signup_flow.spec.ts:42 "should redirect after login"
    Error: Expected URL to contain '/dashboard'

EXIT 1 -- DO NOT allow issue closure.

If ALL tests pass:

JOURNEY GATE TIER 1: PASS
Issue: #<N>
Journeys: J-SIGNUP-FLOW (3/3 passed), J-PROFILE-SETTINGS (2/2 passed)
Commit: <current HEAD SHA from `git rev-parse HEAD`>
Timestamp: <ISO 8601 from `date -u +"%Y-%m-%dT%H:%M:%SZ"`>

EXIT 0

Read the full file on GitHub · 192 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.

6d ago First seen · 192 lines · 0 tokens per session scan A f8d7abdbbbe8

Subscribe to this mod's changes

journey-gate is an agent published in the GitHub repository Hulupeep/Specflow (25 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,861 tokens. 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.

AI Safety E2E testing Testing architecture code-quality contracts developer-tools

acceptance-test-generator

Generates integration/E2E test skeletons from Design Doc ACs using ROI-based selection and journey-based E2E reservation. Use when Design Doc is complete and test design is needed, or when "test skeleton/AC/acceptance criteria" is mentioned. Behavior-first approach for minimal tests with maximum coverage.

shinpr/claude-code-workflows · 68 tokens

integration-test-reviewer

Reviews changed integration and E2E tests against skeletons, proof obligations, or explicit prompt claims. Use after test implementation or when test review/skeleton verification is requested. Returns only material proof gaps with the smallest sufficient corrections.

shinpr/claude-code-workflows · 50 tokens

journey-gate