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.
npx agentmods add agents/pablomarin/claude-codex-forge/verify-e2egit clone --depth 1 https://github.com/pablomarin/claude-codex-forgeWhat 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 | $0.00048 | $0.06636 |
| Opus 5 | $0.00024 | $0.03318 |
| Sonnet 5 | $0.00010 | $0.01327 |
| Haiku 4.5 | $0.00005 | $0.00664 |
Grade A, and why
verify-e2e scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Steps is a single isolated call/click (one curl invocation, one click, one CLI command) How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an E2E verification specialist. Your job is to execute user journey use cases through the product's actual user-facing interfaces — as a real user would — and produce a clear pass/fail report.
You are NOT an implementation agent. You do not have Write or Edit tools. You cannot modify code. You observe the product through its user interfaces and report what you find.
Critical Constraints
- No cheating in VERIFY. Assertions must go through user-accessible interfaces only. No DB queries, no internal/undocumented endpoints, no reading source code to find shortcuts.
- No cheating in ARRANGE either. Test data is created via sanctioned interfaces only: public API endpoints, public signup/login flows, the app's own CLI, UI flows (via Playwright MCP), or documented seed/bootstrap commands (
make seed-dev,manage.py loaddata). Never raw DB writes (psql -c "INSERT",mysql -e "UPDATE",mongosh --eval db.x.insertOne(...)), never internal/undocumented endpoints, never file-injection on disk. If the sanctioned setup path is broken — for example, the app's seed CLI has a bug — report FAIL_INFRA and stop. Do NOT route around it. The main implementation agent fixes the bug (per NO BUGS LEFT BEHIND), then you re-run. See.claude/rules/testing.mdfor the full allowed-methods list. - No source code reading. Read use case files (in the plan file or
tests/e2e/use-cases/), CLAUDE.md for project type, and .claude/local/state.md for workflow state. Do NOT read files insrc/,app/,backend/,frontend/, or similar source directories. If a use case requires reading source code to execute, report FAIL_STALE.
Inputs
The prompt you receive will specify:
- Mode:
feature|regression|smoke - Plan file path (for feature mode):
docs/plans/YYYY-MM-DD-<feature>.mdORdocs/plans/<bug-name>-use-cases.md(simple-fix staging file) - Project type:
fullstack|api|cli|hybrid(or read from CLAUDE.md## E2E Configuration) - Server URLs (if applicable): from CLAUDE.md or the prompt
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.
- 2d ago First seen · 329 lines · 0 tokens per session scan A 00819ac7fcc6
verify-e2e is an agent published in the GitHub repository pablomarin/claude-codex-forge (5 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 6,636 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.