testgen

A test-stub generator that reads verification criteria from a GitHub issue and creates starter test files. A test stub is an unfinished test structure that developers complete with the exact checks.

In plain words
What is it for?
Use it to create test stubs for an issue's scenarios, place them in the expected directories, and summarize the generated work in the issue.
Why use it?
It turns written acceptance and verification requirements into a concrete starting point for testing, reducing manual setup work.

Skill for Claude CodeCodex

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 skills/sequant-io/sequant/testgen
Any agent
npx skills add sequant-io/sequant --skill testgen
Clone the repo
git clone --depth 1 https://github.com/sequant-io/sequant

Made for: Claude Code, Codex.

Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,266 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00012 $0.05266
Opus 5 $0.00006 $0.02633
Sonnet 5 $0.00002 $0.01053
Haiku 4.5 $0.00001 $0.00527

Measured yesterday against content hash 73ffacd5a509, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

testgen 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 yesterday.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

import { exec } from 'child_process';
.claude/skills/testgen/SKILL.md · 714 lines

How it starts

The opening of the file, as written. The whole thing — 714 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Local overrides (read this first). Before following any instruction below, check whether .claude/.local/skills/testgen/overrides.md exists. If it does, read it and treat its contents as authoritative: its instructions take precedence over anything in this skill they conflict with. This is the supported way to tailor /testgen without forking it — overrides.md lives under .claude/.local/, which sequant update and sync never overwrite.

Test Generation Command

You are the "Test Generation Agent" for the current repository.

Purpose

When invoked as /testgen <issue-number>, your job is to:

  1. Read verification criteria from the latest /spec comment on the GitHub issue
  2. Parse each AC's verification method and test scenario
  3. Generate appropriate test stubs based on verification method type
  4. Output stubs to the correct directories with TODO markers
  5. Post a summary comment to the GitHub issue

Invocation

  • /testgen 123 - Generate test stubs for issue #123 based on /spec comment
  • /testgen - Generate stubs for the most recently discussed issue in conversation

Sub-Agent Delegation for Stub Generation

Purpose: Test stub generation is highly mechanical and is delegated to sequant-testgen so the main agent focuses on orchestration.

Upstream caveat: sequant-testgen declares model: haiku, but per anthropics/claude-code#43869 that declaration is currently ignored — the subagent inherits the parent session's model. Older versions of this doc claimed concrete token-cost savings from haiku. Those numbers are not achievable until the upstream fix ships; treat the haiku claim as the intended tier, not the runtime one.

Pattern: Use Agent(subagent_type="sequant-testgen") for:

  1. Parsing verification criteria from /spec comments
  2. Generating individual test stubs from templates
  3. Writing test file content

Benefits:

  • Main agent focuses on orchestration and decisions, not stub templating
  • Designated tier (haiku) will yield token savings once anthropics/claude-code#43869 is fixed; today subagents inherit the parent's model

Read the full file on GitHub · 714 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.

  1. yesterday First seen · 714 lines · 12 tokens per session scan A 73ffacd5a509

Subscribe to this mod's changes

testgen is a skill published in the GitHub repository sequant-io/sequant (1 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 5,266 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

agent-estate

Perpetual autonomous work loop for Claude Code — no end condition, no memory regression, no context overfill. Maintains a persistent ledger across all sessions.

MercuriusDream/agent-estate · 36 tokens

citation-audit

Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations"…

wanshuiyin/Auto-claude-code-research-in-sleep · 86 tokens

paper-illustration

Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.

wanshuiyin/Auto-claude-code-research-in-sleep · 67 tokens

paper-illustration-image2

Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to paper-illustration, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.

wanshuiyin/Auto-claude-code-research-in-sleep · 59 tokens

experiment-plan

Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after research-refine, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty…

wanshuiyin/Auto-claude-code-research-in-sleep · 80 tokens

paper-writing

Workflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.

wanshuiyin/Auto-claude-code-research-in-sleep · 58 tokens