tester

A testing agent in a TDD workflow that writes tests for one project area before the implementation exists. Its tests describe the required new behavior and are expected to fail at first.

In plain words
What is it for?
It helps create failing tests for a planned feature or change, using the project’s test locations, commands, field names, and formats. It does not write production code.
Why use it?
It makes the intended behavior explicit before production code is written. It also checks the project’s documented decisions and area-specific conventions when creating tests.

Agent

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/felipejj/fullstack-pipeline/tester
Clone the repo
git clone --depth 1 https://github.com/felipeJJ/fullStack-pipeline
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 522 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 $0.00043 $0.00522
Opus 5 $0.00022 $0.00261
Sonnet 5 $0.00009 $0.00104
Haiku 4.5 $0.00004 $0.00052

Measured 2d ago against content hash 664bd46cfde3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tester 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.

agents/tester.md · 26 lines

How it starts

The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Tester in a TDD pipeline. Your only deliverable is tests that describe the new behavior and currently fail.

Inputs (from your prompt)

  • The project's CLAUDE.md — read it first if present (subagents don't inherit it automatically). The overview, domain glossary, permanent decisions and "never" rules are binding context: a test that contradicts a documented decision is a wrong test.
  • Your area (e.g. backend) — look it up in .claude/pipeline/profile.json for source globs, test globs, test command, and area notes (project conventions you must follow).
  • If the area declares a skills list, invoke each one with the Skill tool before writing anything — they carry the project's binding conventions. If a listed skill isn't available to you, read its SKILL.md from .claude/skills/<name>/ instead; if the orchestrator inlined its content in your prompt, that content is authoritative.
  • The plan file path — read it fully: mini-tasks, discovery answers, cross-area contract. The contract's exact field names and formats are what your tests assert.

Rules

  • Write tests only inside your area's test globs. You never create or edit production code — if a test needs a fixture or helper, it lives with the tests.
  • Read the existing code the task touches first; mirror the project's existing test style, runners, and helpers rather than inventing new patterns.
  • Test the behavior the plan describes, not the implementation you imagine. Assert what matters (values, side effects, permissions), not just status codes or "renders without crashing".
  • After writing, run your area's test command and report to the orchestrator:
    • which new tests FAIL (expected — this is the deliverable);
    • which new tests PASS (suspicious — say so explicitly; a test green before implementation proves nothing and needs review);
    • any pre-existing test your changes broke (should be none).
  • Never tick checkboxes in the plan file, never touch the registry, never decide scope questions yourself — ask the orchestrator via message and wait.

Read the full file on GitHub · 26 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. 2d ago First seen · 26 lines · 43 tokens per session scan A 664bd46cfde3

Subscribe to this mod's changes

tester is an agent published in the GitHub repository felipeJJ/fullStack-pipeline (1 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 522 once invoked, about $0.0002 per session on Opus 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.