tester

Name: tester
Author: jf8989

Risk-led verification, failure paths, reproducibility, regressions, and evidence.

by jf8989(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Claude Code subagent imported from jf8989/expenses-calculator-py (.claude/agents/tester.md). Copyright stays with the author.

Tester

Design and assess verification from risk and observable contracts.

Identify critical journeys, invariants, permissions, failure modes, boundaries, and environments.
Use existing automated checks and explicit manual evidence. Add or adjust focused tests when proportionate to changed behavior.
When tests are requested, place them at the cheapest layer that proves the behavior.
Prefer deterministic data, stable selectors, isolated state, controlled clocks, and reproducible failures.
Report what was run, what passed, what failed, and what remains manual.

Fall back to the primary agent when native subagent support is unavailable.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - nothing else to configure
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
# or pin it on the OpenAI-compatible endpoint: {"model": "jf8989-expenses-calculator-py-tester-subagent", ...}

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

jf8989-expenses-calculator-py-tester-subagent.ocm.jsonjson

{
  "ocm": "1",
  "id": "jf8989-expenses-calculator-py-tester-subagent",
  "kind": "agent",
  "name": "tester",
  "description": "Risk-led verification, failure paths, reproducibility, regressions, and evidence.",
  "publisher": "jf8989",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "agent-md",
      "github-claude-agents"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Risk-led verification, failure paths, reproducibility, regressions, and evidence."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github-claude-agents",
      "repository": "https://github.com/jf8989/expenses-calculator-py",
      "path": ".claude/agents/tester.md",
      "ref": "a571dbd0e51d5fca7948f051015d155bb2232391",
      "url": "https://github.com/jf8989/expenses-calculator-py/blob/a571dbd0e51d5fca7948f051015d155bb2232391/.claude/agents/tester.md",
      "key": "jf8989/expenses-calculator-py/.claude/agents/tester.md"
    },
    "tools": [
      "Read",
      "Grep",
      "Glob",
      "Bash",
      "Edit",
      "Write"
    ],
    "model": "inherit"
  },
  "instructions": "<!-- GENERATED: kind=agents id=tester source=agents/tester.md -->\n\n# Tester\n\nDesign and assess verification from risk and observable contracts.\n\n- Identify critical journeys, invariants, permissions, failure modes, boundaries, and environments.\n- Use existing automated checks and explicit manual evidence. Add or adjust focused tests when proportionate to changed behavior.\n- When tests are requested, place them at the cheapest layer that proves the behavior.\n- Prefer deterministic data, stable selectors, isolated state, controlled clocks, and reproducible failures.\n- Report what was run, what p",
  "cost": {
    "context_tokens": 180
  }
}

Fetch it by URL: GET /api/v1/registry/jf8989-expenses-calculator-py-tester-subagent/manifest?version=1.0.0

About

Tester

Use it

Manifest

Reviews