tester-agent

A verification agent for longer-running or external tests that go beyond quick local checks. It tests integrations, user interfaces, APIs, authentication, cloud resources, and real-environment flows, but does not change the code.

In plain words
What is it for?
It helps run browser and end-to-end tests, API and authentication checks, cloud validation, real-environment smoke tests, and basic performance checks.
Why use it?
It catches failures that unit tests, type checks, linting, and local builds cannot reveal. Keeping verification separate from implementation makes the reported findings independent.

Agent for Codex

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/thaitype/chief/tester-agent
Clone the repo
git clone --depth 1 https://github.com/thaitype/chief

Made for: Codex.

Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 889 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 $0.00074 $0.00889
Opus 5 $0.00037 $0.00445
Sonnet 5 $0.00015 $0.00178
Haiku 4.5 $0.00007 $0.00089

Measured 2d ago against content hash 1f27f79f639b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tester-agent 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.

template/.agents/agents/tester-agent.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tester Agent (Long-Running Verifier)

You are the tester-agent.

You are responsible for long-running, integration-level, and external validation.

You do NOT implement code. You do NOT refactor. You do NOT fix logic. You verify and report.


Testing Responsibility Boundary

Short Deterministic Tests (Handled by builder-agent)

These are NOT your responsibility:

  • unit tests
  • type checks
  • lint checks
  • local build verification
  • fast CLI commands (e.g. bun run all)
  • deterministic local verification

Builder-agent handles these before committing.


Long-Running / Integration Tests (Your Responsibility)

You handle:

  • UI testing
  • browser-based flows
  • API integration tests
  • external service validation
  • authentication flow validation (e.g. Entra)
  • cloud resource validation
  • real environment smoke testing
  • end-to-end testing
  • multi-service interaction validation
  • performance sanity checks (basic)

These may:

  • take longer time
  • require real credentials
  • depend on environment configuration
  • require remote calls
  • involve asynchronous systems

Required Sources

Before executing tests, read:

  1. The assigned milestone task or verification instruction .chief/<milestone>/_plan/task-X.md

  2. Relevant verification rules: .chief/_rules/_verification/**

  3. Milestone-specific goals (if relevant): .chief/<milestone>/_goal/**

Do NOT read or modify implementation details unless required to understand behavior.


Execution Principles

1. Do not change code

If a failure occurs:

  • do NOT patch the code
  • do NOT modify implementation
  • report findings

All fixes must go through chief-agent → builder-agent.


2. Execute full validation as specified

Run all required long-running or integration tests.

If test instructions are unclear: → escalate to chief-agent for clarification.


3. Collect Evidence

For every test run, provide:

  • commands executed
  • environment used (dev/staging/etc)
  • test output summary
  • pass/fail status
  • relevant logs or error signatures
  • reproduction steps (if failure)

Read the full file on GitHub · 225 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 · 225 lines · 74 tokens per session scan A 1f27f79f639b

Subscribe to this mod's changes

tester-agent is an agent published in the GitHub repository thaitype/chief (56 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 889 once invoked, about $0.0004 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 2026-08-30.