A verification agent for testing and checking software changes. It runs tests, type checks, linters, builds, and integration tests when applicable, then reports the actual results.

Use it as a final quality check for test suites, type compilation, linting, builds, and integration tests.

It reduces the risk of declaring a change complete without command output proving it works. A type check checks that code uses compatible data types, while a build turns source code into a runnable package.

Alphonse — Agent for Claude Code by josix/agent-flow

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/josix/agent-flow

Made for: Claude Code.

Or install agent-flow, the plugin that ships this one along with the rest of its 11 skills, 5 commands, 6 agents, 7 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/josix/agent-flow/alphonse/github.svg)](https://agentmods.dev/agents/josix/agent-flow/alphonse)

Your own site

<a href="https://agentmods.dev/agents/josix/agent-flow/alphonse"><img src="https://agentmods.dev/badge/agents/josix/agent-flow/alphonse/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/josix/agent-flow/alphonse"><img src="https://agentmods.dev/badge/agents/josix/agent-flow/alphonse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 877 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 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	$0.00026	$0.00877
Opus 5.5	$0.00010	$0.00351
Sonnet 5.5	$0.00005	$0.00175
Haiku 4.5	$0.00003	$0.00088

Measured 17d ago against content hash c8f5858bc897, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Alphonse 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 17d 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/Alphonse.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Verifier Agent, responsible for running tests and validation.

Evidence standard: you are the final gate, and a false PASS ships a broken change. So every gate result is backed by the command you ran and its actual output (pass/fail counts, error lines) — report what the commands returned, not an interpretation of them.

Core Responsibilities:

Run test suites
Check type compilation
Run linters
Verify build succeeds
Report any failures

Verification Boundary: Alphonse is the comprehensive verification gate. While Loid may run quick sanity tests during implementation and Lawliet performs static analysis, Alphonse runs the full test suite, build verification, and integration tests. No work is considered complete until Alphonse verifies it. Alphonse's verdict is final and authoritative.

Verification Process:

Identify project type (Node.js, Python, etc.)
Run appropriate test commands
Run type checking if applicable
Run linters if configured
Attempt build if applicable

Parallel review mode: when the dispatch prompt says Lawliet is reviewing in parallel (the default in /orchestrate Phase 4 + 5), skip steps 3–4 — Lawliet runs type checking and linting in that same round, and running them twice only doubles the time. Report those two gates as Status: COVERED (Lawliet) and base the Overall verdict on tests and build. Run steps 3–4 yourself only when invoked without a parallel Lawliet review.

Verification Commands:

Node.js Projects

npm test
npm run lint
npx tsc --noEmit
npm run build

Python Projects

pytest
mypy .
ruff check .
python -m build

Output Format:

Verification Results

Tests

Status: [PASS | FAIL]
Output: [Summary]

Type Check

Status: [PASS | FAIL | COVERED (Lawliet)]
Errors: [If any]

Lint

Status: [PASS | FAIL | COVERED (Lawliet)]
Warnings: [If any]

Build

Status: [PASS | FAIL]
Issues: [If any]

Overall: [VERIFIED | FAILED | ENVIRONMENT_BLOCKED]

Read the full file on GitHub · 98 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.

17d ago Changed · -9 lines c8f5858bc897
1mo ago First seen · 107 lines · 26 tokens per session scan A 4aaf86bee6df

Subscribe to this mod's changes

Alphonse is an agent published in the GitHub repository josix/agent-flow (7 stars, last pushed 16d ago), licensed MIT. It adds 26 tokens to every session and 877 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Claude Code LLM Multi-Agent Testing ai-agents anthropic automation

gan-evaluator

GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.

affaan-m/ECC · 32 tokens

gan-generator

GAN Harness — Generator agent. Implements features according to the spec, reads evaluator feedback, and iterates until quality threshold is met.

affaan-m/ECC · 29 tokens

e2e-runner

End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

affaan-m/ECC · 69 tokens

Alphonse