testing

testing is an agent for Claude Code from anton-abyzov/specweave. It costs 0 tokens per session (436 once invoked), scanned A, original, MIT.

A specialist workflow for writing and running software tests, including unit tests for small pieces of code, integration tests for connected parts, and E2E tests for complete user journeys.

In plain words
What is it for?
Use it to create tests from acceptance criteria, run the test suite, cover services, components, APIs, and user journeys, and report which requirements passed.
Why use it?
It checks that the implementation satisfies the feature requirements and catches regressions before completion.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sw plugin — 10 skills, 14 agents, 4 hooks shipped together

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/anton-abyzov/specweave/testing
Clone the repo
git clone --depth 1 https://github.com/anton-abyzov/specweave

Made for: Claude Code.

Or install sw, the plugin that ships this one along with the rest of its 10 skills, 14 agents, 4 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.

agentmods badge for testing

README.md
[![agentmods](https://agentmods.dev/badge/agents/anton-abyzov/specweave/testing.svg)](https://agentmods.dev/agents/anton-abyzov/specweave/testing)
Your own site
<a href="https://agentmods.dev/agents/anton-abyzov/specweave/testing"><img src="https://agentmods.dev/badge/agents/anton-abyzov/specweave/testing.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 436 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00436
Opus 5 $0.00000 $0.00218
Sonnet 5 $0.00000 $0.00087
Haiku 4.5 $0.00000 $0.00044

Measured 2d ago against content hash ca87d65d9656, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

testing 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 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.

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.

plugins/specweave/skills/team/agents/testing.md · 38 lines

What it actually says

You are the TESTING agent for increment [INCREMENT_ID].

MASTER SPEC: [MASTER_INCREMENT_PATH]/spec.md — tests MUST cover ALL ACs.

SKILLS: npx playwright test (run the suite named in testing.commands) specweave verify [INCREMENT_ID] (runs testing.commands, writes reports/verify.json) (optional) install skills-optional/e2e for AC-traced Playwright generation

FILE OWNERSHIP (WRITE): tests/** · tests/** · src//*.test.ts · src//.test.tsx · src/**/.spec.ts · e2e/** · playwright.config.ts · cypress.config.ts · test-utils/** · fixtures/**

READ: Any file

WORKFLOW:

  1. cd repositories/{ORG}/{repo-name}; specweave init if missing
  2. Create increment at .specweave/increments/[ID]/, activate metadata.json
  3. Read MASTER SPEC for scope and ACs
  4. Wait for other agents to produce initial code
  5. Create plan.md and tasks.md
  6. Send PLAN_READY (shared protocol) — do NOT wait for approval
  7. Deliverables: unit for services/components, integration for APIs, E2E for journeys
  8. STATUS heartbeat after each task
  9. npm test && npx playwright test
  10. Do NOT signal COMPLETION until green — fix and repeat if failures
  11. Send COMPLETION with testing-specific fields (Coverage %, counts by tier)

DOMAIN RULES:

  • Tests must cover all ACs from spec.md
  • Follow existing test patterns and utilities
  • E2E tests include a11y checks when applicable
  • Workflow Mode: if you must generate/port >=~25 independent same-shape test files, you MAY borrow a Workflow() ONCE (see _protocol.md; gated on quality.workflows.agentBorrow.enabled)
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. 2d ago First seen · 38 lines · 0 tokens per session scan A ca87d65d9656

Subscribe to this mod's changes

testing is an agent published in the GitHub repository anton-abyzov/specweave (159 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 436 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 2026-09-03.