What is ijfw-e2e-runner?

A pre-release test agent that runs the normal install, update, and uninstall process in a temporary folder. It checks only the parts affected by the current Git changes before a release.

Use it to compare changes with the main branch, package affected components, test installation updates and removal, and skip safely when only documentation changed.

It exposes packaging and installation problems early, before the more extensive release checks run.

ijfw-e2e-runner — Agent for Claude Code by FerroxLabs/ijfw

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.

Clone the repo

git clone --depth 1 https://github.com/FerroxLabs/ijfw

Made for: Claude Code.

Or install ijfw, the plugin that ships this one along with the rest of its 34 skills, 22 commands, 37 agents, 6 hooks.

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/ferroxlabs/ijfw/ijfw-e2e-runner/github.svg)](https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-e2e-runner)

Your own site

<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-e2e-runner"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-e2e-runner/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-e2e-runner"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-e2e-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,119 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.

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	$0.00029	$0.01119
Opus 5.5	$0.00012	$0.00448
Sonnet 5.5	$0.00006	$0.00224
Haiku 4.5	$0.00003	$0.00112

Measured 1mo ago against content hash 663a8983b28e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

ijfw-e2e-runner scanned grade D 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 1mo 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Do not run as root or with sudo (npm install -g without --prefix would).

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

8. **Cleanup** -- `rm -rf <tmp>` unless `keep_tmp: true`.

claude/agents/ijfw-e2e-runner.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the canonical install + update + uninstall against the current HEAD in a throwaway tmpdir, mirror what users do, surface ship-blockers earlier than the smoke harness does. v1.4.4 ship-gate ran the smoke 3x to find its bugs; this agent makes the first pass cheap enough to run pre-merge.

ROLE

Ship-gate pre-flight. The smoke harness is comprehensive but expensive (30+ gates, multiple modes). This agent runs the diff-scoped subset -- just the install/update/uninstall flow against the changes in the current phase -- so a doomed PR is killed at review time, not at ship time.

PROCESS

Compute diff scope -- git diff --name-only main...HEAD to learn which packages/components changed. If installer/ touched -> run install. If mcp-server/ touched -> run install (because installer pulls it). If only docs touched -> emit SKIP_DOCS_ONLY + PASS.
Create fixture tmpdir -- mktemp -d -t ijfw-e2e-XXXXXX. Record path in artifact. Confirm not under repo root.
Stage current HEAD as a publishable tarball:
- cd installer && npm pack --pack-destination <tmp>
- cd mcp-server && npm pack --pack-destination <tmp>
- Verify both .tgz files exist.
Canonical install -- in tmpdir:
- npm install -g <tmp>/ijfw-install-*.tgz (or --prefix <tmp>/prefix to avoid touching the user's global modules; prefer the prefix form).
- Run <tmp>/prefix/bin/ijfw --version -- assert matches package.json.
- Run <tmp>/prefix/bin/ijfw doctor -- capture output; assert exit 0.
Canonical update -- re-install from same tarball:
- npm install -g --force <tmp>/ijfw-install-*.tgz
- Re-run ijfw --version; assert idempotent.
Canonical uninstall:
- npm uninstall -g @ijfw/install
- Assert ijfw no longer on PATH.
Write artifacts:
- .planning/<phase>/E2E.md -- flow log + verdicts per step.
- .ijfw-test/<phase>-e2e.fixture.json -- captured outputs (versions, doctor output, timestamps).

Read the full file on GitHub · 112 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.

1mo ago First seen · 112 lines · 29 tokens per session scan D 663a8983b28e

Subscribe to this mod's changes

ijfw-e2e-runner is an agent published in the GitHub repository FerroxLabs/ijfw (214 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,119 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code E2E testing Testing ai-agents ai-coding codex cursor developer-tools

qa-tester

Creates and runs test suites. Use after implementing features to generate unit tests, integration tests, and E2E tests.

faizkhairi/claude-code-blueprint · 28 tokens

test-case-result-validator

Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline.

griddynamics/rosetta · 34 tokens

Metis Verifier

L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.

Wholiver/metis · 36 tokens

test-generator

Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.

travisjneuman/.claude · 27 tokens

checker

Fresh-context adversarial verification of completed work. Give it the claimed outcome plus the relevant diff or paths; it independently reruns tests, exercises the affected flow, probes edge cases, and returns CONFIRMED or REFUTED. Read-and-run only; it never plans, edits, or fixes anything.

cordwainersmith/Claudoscope · 63 tokens

test-debugger

Diagnoses flaky or failing Playwright tests using systematic taxonomy. Invoked by /pw:fix when a test needs deep analysis including running tests, reading traces, and identifying root causes.

adriannoes/awesome-agentic-ai · 41 tokens

ijfw-e2e-runner