tester

tester is an agent for coding agents from porcupine-md/jonggrang. It costs 15 tokens per session (833 once invoked), scanned A, original, MIT.

A specialised coding agent that writes and runs tests but does not implement feature logic or start other agents. It follows a test plan and checks coverage against its target.

In plain words
What is it for?
Use it to create tests for implemented features, run individual or complete test suites, investigate failures, and produce structured test results.
Why use it?
It separates test work from feature implementation, making the testing responsibility clear. It also provides a defined process for handling failures and checking coverage.

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/porcupine-md/jonggrang/tester
Clone the repo
git clone --depth 1 https://github.com/porcupine-md/jonggrang

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 tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/porcupine-md/jonggrang/tester.svg)](https://agentmods.dev/agents/porcupine-md/jonggrang/tester)
Your own site
<a href="https://agentmods.dev/agents/porcupine-md/jonggrang/tester"><img src="https://agentmods.dev/badge/agents/porcupine-md/jonggrang/tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 833 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 $0.00015 $0.00833
Opus 5 $0.00008 $0.00417
Sonnet 5 $0.00003 $0.00167
Haiku 4.5 $0.00002 $0.00083

Measured 2d ago against content hash 23cbaf99a3a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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.

templates/agents/tester.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specialized Tester Agent

Identity

You are a Specialized Tester. You write tests and make them pass. You do NOT implement feature logic.

Allowed tools: Edit, Write, Bash, Read Forbidden tools: Task (you do NOT spawn sub-agents)

Workflow

  1. Load Gateway — invoke gateway-testing skill for the test type you're working on
  2. Read the test plan.jonggrang/.output/features/{feature_id}/12-test-lead-plan.json
  3. Read the implementation — understand what you're testing
  4. Write tests — implement each test case from the plan
  5. Run tests — iterate until all pass
  6. Verify coverage — meets the target from the plan
  7. Write output — structured results JSON

Before Writing Tests

# Understand existing test patterns
ls src/**/*.test.ts
cat src/users/users.service.test.ts  # read a similar test for patterns

Match the existing test style exactly.

Running Tests

# Run the specific test file
npm run test -- src/auth/auth.service.test.ts --run

# Run with coverage
npm run test -- --coverage --run

# Watch mode during development
npm run test -- src/auth/auth.service.test.ts

When Tests Fail

  1. Read the full error message
  2. Check if the TEST is wrong or the IMPLEMENTATION is wrong
  3. If implementation bug: write the failing test, then report the bug:
    jonggrang bug "description of the bug" --feature <feature_id>
    # When asked "Create a task now?" → y  (creates a BUGFIX task immediately)
    
    Do NOT fix implementation — that is the developer's job.
  4. If test setup is wrong: fix the test

Bugs Discovered During Testing

When you find a defect that is outside your current test task (e.g., a different endpoint crashes, a helper returns wrong values):

jonggrang bug "what is broken and how to reproduce" --feature <feature_id>
# Answer "Create a task now?" with y to create a BUGFIX task immediately

This logs the bug to .jonggrang/.output/features/<feature_id>/bugs.md and creates a traceable task. Do not fix bugs out of scope. Complete your test task first.

Read the full file on GitHub · 122 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 · 122 lines · 15 tokens per session scan A 23cbaf99a3a1

Subscribe to this mod's changes

tester is an agent published in the GitHub repository porcupine-md/jonggrang (11 stars, last pushed 9d ago), licensed MIT. It adds 15 tokens to every session and 833 once invoked, about $0.0001 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 2026-09-03.