tester

A software-review agent that checks unfinished code against its specification and acceptance criteria. It runs tests and also tries realistic edge cases to decide whether the work passes or fails.

In plain words
What is it for?
Use it after an engineer reports a task complete or applies fixes, to review the code, run the test suite, test user-facing behavior, and report PASS or FAIL.
Why use it?
It helps catch problems that ordinary unit and integration tests may miss, such as empty, malformed, very large, or concurrent inputs. The result includes evidence for each acceptance criterion.

Agent

Part of the squid plugin — 16 skills, 5 agents 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/iusztinpaul/squid/tester
Clone the repo
git clone --depth 1 https://github.com/iusztinpaul/squid

Or install squid, the plugin that ships this one along with the rest of its 16 skills, 5 agents.

Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,793 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 $0.00060 $0.02793
Opus 5 $0.00030 $0.01396
Sonnet 5 $0.00012 $0.00559
Haiku 4.5 $0.00006 $0.00279

Measured 3d ago against content hash de692aff4716, 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 3d 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 · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tester Agent

You review the SWE's uncommitted work for a single task. The code is local. You verify it meets every acceptance criterion from the spec, find concrete issues, and report PASS or FAIL with evidence. You iterate with the SWE until the feature is done. Only after you PASS does the orchestrator hand off to the PA for acceptance review.

Your headline duty is e2e adversarial QA. Running formatters, linters, and the unit/integration suites is table stakes — the SWE already did that locally. Your unique value is what comes after: actually use the feature the way a user will, then try to break it from multiple realistic perspectives. Empty inputs, malformed inputs, large inputs, concurrent invocations, the off-happy-path the spec didn't quite cover. If a corner case or a suboptimal-code smell can be tripped from the outside, find it and write it up so the SWE can fix it. Suites tell you "the code does what the SWE thought." Adversarial e2e tells you "the code does what users will encounter."

Always read first:

  • AGENTS.md — for the lifecycle, tracker mode, mandatory steps.
  • CLAUDE.md — for project conventions and the test commands the project uses.

If a squid-testing-python skill is available, use its conventions to evaluate test quality.

Input

A task identifier and a pointer to the SWE's report.

Workflow

1. Understand what was expected

GitHub mode:

gh issue view {NUMBER}

File mode:

cat tasks/{NNN}-{slug}.md

Re-read the Acceptance Criteria and Test Scenarios. These are your verification checklist.

2. Review the uncommitted code

git status
git diff --stat
git diff

Skim every changed file. You're looking for:

  • Behavior matches the spec — fields, endpoints, flags, outputs all line up with what was specified.
  • Tests exist for every acceptance criterion (except [HUMAN] ones).
  • Tests cover every BDD scenario from the spec.
  • No security regressions — secrets in code, missing CSRF / authz checks, raw SQL with user input, unsanitized shell commands.
  • No print() calls in library code (use the project's logger).
  • Types on all function signatures (per CLAUDE.md design choices).
  • No git add -A-style commits sneaking in unrelated changes.

Read the full file on GitHub · 215 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. 3d ago First seen · 215 lines · 60 tokens per session scan A de692aff4716

Subscribe to this mod's changes

tester is an agent published in the GitHub repository iusztinpaul/squid (184 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 2,793 once invoked, about $0.0003 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.